© 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. 8714
    Prev
    Next
    INDEX
    Explanations

    seems to be capturing punctuation and grammatical connectives, indicating possible sentence boundaries or discourse structure.

    oai_token-act-pair · gemini-2.0-flash

    End of sentence or clause

    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
     contemplate
    -0.60
    IntoConstraints
    -0.59
    hawatir
    -0.58
    Rhestr
    -0.54
    vitis
    -0.53
     think
    -0.52
     ProtoMessage
    -0.52
    iomanip
    -0.49
    vember
    -0.49
    ruik
    -0.49
    POSITIVE LOGITS
     propOrder
    0.75
    aarrggbb
    0.61
    UnusedPrivate
    0.60
    Obrázky
    0.57
    SourceChecksum
    0.56
    setVerticalGroup
    0.55
     AssemblyCulture
    0.54
    </thead>
    0.54
     therefor
    0.54
     thus
    0.54
    Activations Density 2.560%

    No Known Activations