© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11386
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially javascript and other web technologies

    oai_token-act-pair · gemini-2.0-flash

    names and identifiers in coding

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

    Code

    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
     "
    -2.14
     “
    -2.06
     ‘
    -1.77
     '
    -1.77
     «
    -1.71
     „
    -1.66
    「
    -1.56
     ''
    -1.42
     ‘‘
    -1.41
     ``
    -1.38
    POSITIVE LOGITS
     Efq
    1.34
     myſelf
    1.25
     $_"
    1.23
     itſelf
    1.21
     ſche
    1.11
     raiſ
    1.10
     ſind
    1.07
     ―――――
    1.06
     Jefus
    1.05
     iſt
    1.05
    Activations Density 1.714%

    No Known Activations