© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3497
    Prev
    Next
    INDEX
    Explanations

    occurrences of characters in a narrative

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Say
    -0.47
    __);
    -0.46
     accomp
    -0.45
    MAJ
    -0.43
    UpdatedAt
    -0.42
    tissage
    -0.41
     bewer
    -0.41
     SAY
    -0.41
    say
    -0.41
    opensource
    -0.40
    POSITIVE LOGITS
    Tembelea
    0.82
    sizeCache
    0.65
    SharedCtor
    0.62
    gameserver
    0.62
     nahilalakip
    0.61
     gas
    0.60
     hâte
    0.60
    AndEndTag
    0.60
     виправивши
    0.59
     varandra
    0.59
    Activations Density 1.099%

    No Known Activations