© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9968
    Prev
    Next
    INDEX
    Explanations

    hyphenated phrases and parenthetical statements

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    -1.91
    private
    -0.81
     The
    -0.74
    rethe
    -0.60
    akaian
    -0.60
    Portail
    -0.56
     their
    -0.56
    Sucesor
    -0.56
     suaminya
    -0.54
    InjectAttribute
    -0.54
    POSITIVE LOGITS
    THE
    0.94
    the
    0.79
    KommentareTeilen
    0.66
    multicolumn
    0.52
     considérons
    0.49
    tf
    0.48
    ępnie
    0.48
    ❋
    0.47
     gewor
    0.44
    tor
    0.44
    Activations Density 7.661%

    No Known Activations