© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14702
    Prev
    Next
    INDEX
    Explanations

    country and city names

    oai_token-act-pair · gemini-2.0-flash

    place names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    Rüyada
    -0.60
    ]_{\
    -0.49
    ifel
    -0.48
    </tfoot>
    -0.47
    ;">
    -0.44
    ranean
    -0.43
    UnsafeEnabled
    -0.43
    emie
    -0.43
     Tax
    -0.43
    token
    -0.42
    POSITIVE LOGITS
    ftagPool
    0.69
    InvalidProtocol
    0.61
     HasFactory
    0.59
    RegistryLite
    0.56
    CppCodeGen
    0.55
     @"/
    0.54
    Referencie
    0.54
    ########.
    0.53
    PostExecute
    0.53
     Chriftian
    0.52
    Activations Density 0.250%

    No Known Activations