© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7770
    Prev
    Next
    INDEX
    Explanations

    things that are left

    oai_token-act-pair · gemini-2.0-flash

    isolation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    setContentType
    -0.64
    InvalidProtocol
    -0.63
     MainAxisSize
    -0.61
     Paglinawan
    -0.58
    OrWhiteSpace
    -0.58
     ddelweddau
    -0.56
    WireFormatLite
    -0.56
    WebElementEntity
    -0.55
    bootstrapcdn
    -0.55
    CppCodeGen
    -0.55
    POSITIVE LOGITS
     alone
    0.64
     Alone
    0.60
     fallow
    0.55
     ALONE
    0.54
     unattended
    0.54
     untreated
    0.53
     aid
    0.51
     lonely
    0.50
    Aid
    0.50
     Aid
    0.49
    Activations Density 1.358%

    No Known Activations