© 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. 6746
    Prev
    Next
    INDEX
    Explanations

    the term "exp" followed by numbers, or code-related terms like "node", "sexp", "match", and "empty"

    oai_token-act-pair · gemini-2.0-flash

    exp

    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
     purpoſe
    -1.43
     itſelf
    -1.30
     pleaſure
    -1.27
     Majefty
    -1.25
     houſe
    -1.23
     raiſ
    -1.23
     Monfieur
    -1.21
     ſche
    -1.20
     ſmall
    -1.20
     leſs
    -1.19
    POSITIVE LOGITS
     
    0.78
    1
    0.75
    A
    0.74
    a
    0.71
    D
    0.69
    e
    0.67
    ↵↵
    0.66
    P
    0.65
    C
    0.65
    M
    0.65
    Activations Density 0.717%

    No Known Activations