© 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. 8354
    Prev
    Next
    INDEX
    Explanations

    code blocks that contain branching logic like if statements and loops

    oai_token-act-pair · gemini-2.0-flash

    Code and special characters

    np_max-act-logits · 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
    cerely
    -0.60
    LookAnd
    -0.57
    Vibr
    -0.55
     Ninth
    -0.54
     Shet
    -0.54
    annel
    -0.53
    nsf
    -0.53
    sibirsk
    -0.52
     Dir
    -0.52
    inados
    -0.52
    POSITIVE LOGITS
    __':
    0.82
    __":
    0.79
    __':
    0.79
    __":
    0.67
     Wiktionnaire
    0.49
    Numerology
    0.48
     referenties
    0.47
    EndContext
    0.47
    tvguidetime
    0.47
    aarrggbb
    0.46
    Activations Density 1.476%

    No Known Activations