© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11686
    Prev
    Next
    INDEX
    Explanations

    words related to business-to-business sales of GPS tracking devices and services

    oai_token-act-pair · gemini-2.0-flash

    will

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     mourut
    -0.66
     skydd
    -0.65
     gants
    -0.63
     voks
    -0.62
     ContentValues
    -0.60
     batteria
    -0.59
     specchio
    -0.58
     EconPapers
    -0.58
     rembour
    -0.58
    AutoScale
    -0.56
    POSITIVE LOGITS
    jooq
    0.65
    oa̍t
    0.57
    erunner
    0.52
    ècie
    0.50
    üyada
    0.49
     подо
    0.48
    kloped
    0.48
    oredCriteria
    0.47
    SerializedName
    0.44
    клопе
    0.43
    Activations Density 2.788%

    No Known Activations