© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 6749
    Prev
    Next
    INDEX
    Explanations

    a jumble of rare words, code snippets, and parts of words

    oai_token-act-pair · gemini-2.0-flash

    possession, authority

    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
    all
    -0.79
    out
    -0.73
    Repost
    -0.66
    SourceChecksum
    -0.63
    στή
    -0.63
    Portale
    -0.60
    siębior
    -0.59
     man
    -0.57
    mybatisplus
    -0.57
    υτό
    -0.56
    POSITIVE LOGITS
    tvguidetime
    0.73
     &___
    0.63
     الحره
    0.63
    parsedMessage
    0.57
    GEBURTS
    0.57
    ConstraintMaker
    0.56
     AssemblyProduct
    0.56
     tslint
    0.55
     către
    0.54
    lankton
    0.54
    Activations Density 2.508%

    No Known Activations