© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11281
    Prev
    Next
    INDEX
    Explanations

    superlative adjectives and ordinal numbers

    oai_token-act-pair · gemini-2.0-flash

    terms related to firsts or notable mentions

    np_token-act-pair-logits · gpt-4o-mini

    beginnings or main components

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     als
    -0.40
    only
    -0.36
    sed
    -0.36
    於
    -0.36
     tr
    -0.35
    yarnpkg
    -0.35
     Only
    -0.35
    ,
    -0.35
     din
    -0.35
     kaynağından
    -0.34
    POSITIVE LOGITS
     itſelf
    0.87
     requirement
    0.84
     pleaſure
    0.82
     thing
    0.81
     numberWith
    0.79
    requirement
    0.78
     resourceCulture
    0.77
     mistake
    0.75
     ingredient
    0.75
     ſtate
    0.75
    Activations Density 2.357%

    No Known Activations