© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 16256
    Prev
    Next
    INDEX
    Explanations

    miscellaneous punctuation and stop words throughout many different kinds of documents.

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     the
    -0.98
    ,
    -0.89
     to
    -0.85
     and
    -0.85
     in
    -0.78
     a
    -0.77
     an
    -0.76
     of
    -0.76
     that
    -0.75
    .
    -0.75
    POSITIVE LOGITS
    OGND
    1.19
     anún
    0.90
     auroit
    0.86
     متعلقه
    0.85
    ArgsConstructor
    0.85
     varandra
    0.84
     avoient
    0.83
     feroit
    0.83
     étoient
    0.83
    +#+#
    0.82
    Activations Density 7.322%

    No Known Activations