© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 6303
    Prev
    Next
    INDEX
    Explanations

    the curly brace characters in the code blocks

    oai_token-act-pair · gemini-2.0-flash

    tokens starting with a whitespace character

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

    Code fragments

    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
    ImageContext
    -1.01
    RectangleBorder
    -1.01
     InputDecoration
    -0.86
    atase
    -0.81
    HideFlags
    -0.79
     lenker
    -0.76
    extAlignment
    -0.74
     myſelf
    -0.74
    WireFormatLite
    -0.73
    BibitemShut
    -0.73
    POSITIVE LOGITS
     «
    0.44
     
    0.44
     ma
    0.41
     im
    0.41
     I
    0.41
     ten
    0.40
     des
    0.40
     pri
    0.40
     erf
    0.39
     qu
    0.39
    Activations Density 1.190%

    No Known Activations