© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15792
    Prev
    Next
    INDEX
    Explanations

    the word "many" (and to a lesser extent, similar words like "multiple" and "several").

    oai_token-act-pair · gemini-2.0-flash

    many

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     many
    -2.92
    many
    -2.31
    Many
    -1.97
     muchos
    -1.95
     Many
    -1.91
     многих
    -1.90
     muitos
    -1.89
     многие
    -1.83
     molte
    -1.83
     många
    -1.82
    POSITIVE LOGITS
    8
    0.57
    »
    0.57
    9
    0.55
    5
    0.54
    lasyon
    0.54
    ленко
    0.54
    %
    0.54
    «
    0.53
    3
    0.53
    ist
    0.53
    Activations Density 3.294%

    No Known Activations