© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10490
    Prev
    Next
    INDEX
    Explanations

    verbs

    oai_token-act-pair · gemini-2.0-flash

    diminishing

    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
    +#+#
    -1.02
     myſelf
    -1.01
     Efq
    -1.01
    tagHelperRunner
    -0.95
     itſelf
    -0.94
     ―――――
    -0.93
     تانيه
    -0.91
     himſelf
    -0.88
     doubtnut
    -0.87
     dieß
    -0.86
    POSITIVE LOGITS
     to
    0.69
     for
    0.68
     into
    0.67
    .
    0.65
    ,
    0.64
     in
    0.57
     with
    0.54
     its
    0.53
     toward
    0.52
     is
    0.52
    Activations Density 8.628%

    No Known Activations