© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6762
    Prev
    Next
    INDEX
    Explanations

    a variety of different types of words and does not have one unifying theme.

    oai_token-act-pair · gemini-2.0-flash

    computer code

    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
    '
    -1.20
    ’
    -1.06
    -
    -0.93
    .
    -0.90
    ,
    -0.84
    _
    -0.82
    <eos>
    -0.69
    /
    -0.69
     (
    -0.65
    (
    -0.63
    POSITIVE LOGITS
     myſelf
    1.44
     houſe
    1.42
     Efq
    1.41
     Monfieur
    1.41
     pleaſure
    1.40
     ſtate
    1.38
     ſeveral
    1.34
     Houſe
    1.34
     Majefty
    1.33
     Jefus
    1.32
    Activations Density 14.407%

    No Known Activations