© 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. 11426
    Prev
    Next
    INDEX
    Explanations

    java code imports from the apache clerezza library

    oai_token-act-pair · gemini-2.0-flash

    technical terms related to Apache

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

    Apache software and 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
    īm
    -0.46
    立
    -0.45
     special
    -0.45
     man
    -0.44
    formis
    -0.44
    пи
    -0.43
    man
    -0.43
     Organ
    -0.43
    andi
    -0.42
    copo
    -0.42
    POSITIVE LOGITS
     ویکی‌پدیای
    0.87
     kaynağından
    0.83
     beginnetje
    0.83
    Personensuche
    0.82
    enumi
    0.81
     otomatig
    0.80
    msgTypes
    0.79
    WireFormatLite
    0.79
    tagHelperRunner
    0.78
    UrlResolution
    0.75
    Activations Density 0.444%

    No Known Activations