© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9204
    Prev
    Next
    INDEX
    Explanations

    language related to patent claims and technical specifications.

    oai_token-act-pair · gemini-2.0-flash

    claim

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     nonché
    -0.69
    sowie
    -0.66
    <bos>
    -0.66
     valamint
    -0.64
     sekä
    -0.60
     sowie
    -0.59
     also
    -0.59
    also
    -0.57
     oraz
    -0.56
     samt
    -0.54
    POSITIVE LOGITS
    帖最后由
    0.65
     بيها
    0.63
    μως
    0.63
    EDEFAULT
    0.61
     ProtoMessage
    0.59
    gway
    0.58
    maline
    0.56
    raulic
    0.55
     Hame
    0.54
     fortunes
    0.53
    Activations Density 0.716%

    No Known Activations