© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14719
    Prev
    Next
    INDEX
    Explanations

    code diffs

    oai_token-act-pair · gemini-2.0-flash

    + and #

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    SourceChecksum
    -0.71
     transfieras
    -0.69
    NUMX
    -0.66
    ftagPool
    -0.66
    AndEndTag
    -0.63
    CHELL
    -0.62
    ThroughAttribute
    -0.62
    <?
    -0.62
    UnitTesting
    -0.61
    "},
    -0.60
    POSITIVE LOGITS
     TestBed
    0.58
    Искәрмәләр
    0.57
    eger
    0.54
     térmico
    0.53
    missie
    0.48
     Aéroport
    0.48
     térm
    0.47
    اديم
    0.46
    cería
    0.46
    انجليز
    0.46
    Activations Density 6.122%

    No Known Activations