© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13084
    Prev
    Next
    INDEX
    Explanations

    JSON-like data structures containing numbers and/or specific characters, suggesting it might be parsing code or configuration files.

    oai_token-act-pair · gemini-2.0-flash

    coding keywords and symbols

    np_token-act-pair-logits · gpt-4o-mini

    }

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    h
    -0.51
    rett
    -0.50
     ponte
    -0.49
    int
    -0.49
     unwarranted
    -0.48
    t
    -0.47
     Albion
    -0.46
    Align
    -0.46
     Righ
    -0.46
     shadowed
    -0.45
    POSITIVE LOGITS
    ReusableCell
    0.84
    ScopeManager
    0.73
     AssemblyCulture
    0.73
     '\\;'
    0.71
     useCallback
    0.71
     HasFactory
    0.67
     bezeichneter
    0.66
    providedIn
    0.65
    مراجع
    0.64
    Datuak
    0.64
    Activations Density 1.950%

    No Known Activations