© 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. 4987
    Prev
    Next
    INDEX
    Explanations

    mentions of things being built or changed in a specific location

    oai_token-act-pair · gemini-2.0-flash

    parking

    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
    MigrationBuilder
    -1.09
    parsedMessage
    -0.87
     الحره
    -0.87
     ISNI
    -0.84
    OGND
    -0.83
    RTEE
    -0.82
     estekak
    -0.81
    ########.
    -0.81
     referrerpolicy
    -0.78
    fromCharCode
    -0.78
    POSITIVE LOGITS
     me
    0.55
     G
    0.48
     g
    0.46
     trans
    0.44
     l
    0.43
     drop
    0.43
    цей
    0.42
    ėj
    0.42
     cor
    0.41
     sub
    0.41
    Activations Density 2.632%

    No Known Activations