© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2226
    Prev
    Next
    INDEX
    Explanations

    a combination of names, words related to chemistry, and possibly words from Japanese pop-culture

    oai_token-act-pair · 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
     <=",
    -0.72
    HtmlAttribute
    -0.70
    principalColumn
    -0.69
     Biôgrafia
    -0.68
     resourceCulture
    -0.65
    ритори
    -0.65
    uxxxx
    -0.64
     Majefty
    -0.63
    SourceChecksum
    -0.62
    InvalidProtocol
    -0.61
    POSITIVE LOGITS
    onAttach
    0.44
    bangan
    0.40
     valign
    0.40
     cible
    0.39
     dy
    0.39
    GeneratedCode
    0.39
     región
    0.39
     echte
    0.38
    inary
    0.38
    nostic
    0.37
    Activations Density 0.946%

    No Known Activations