© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5451
    Prev
    Next
    INDEX
    Explanations

    words and short phrases related to problem solving and recommendations in a variety of domains including job searching, interpersonal relationships, computer programming, or travel.

    oai_token-act-pair · gemini-2.0-flash

    Finding best approach/solution

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unknownFields
    -0.61
    FormTagHelper
    -0.61
    UOUS
    -0.57
    posedge
    -0.50
     JpaRepository
    -0.49
    genstein
    -0.48
     "..\..\
    -0.47
    __((
    -0.47
     lenker
    -0.47
    HasForeignKey
    -0.46
    POSITIVE LOGITS
    ]")]
    0.64
     risol
    0.62
    ंदीखरीदारी
    0.60
     Shelter
    0.56
     Currents
    0.53
    Injectable
    0.52
    findpost
    0.52
     companyId
    0.52
    PreferredItem
    0.52
    ffindor
    0.51
    Activations Density 14.641%

    No Known Activations