© 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. 11261
    Prev
    Next
    INDEX
    Explanations

    PHP code

    oai_token-act-pair · gemini-2.0-flash

    code-related keywords or functions

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

    Computer 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
    InvalidProtocol
    -0.54
    IsContent
    -0.50
     مض
    -0.49
     Réponses
    -0.49
    uldades
    -0.48
    uxxxx
    -0.47
    deelte
    -0.47
    NOUN
    -0.46
    orsese
    -0.46
    undet
    -0.44
    POSITIVE LOGITS
     виправивши
    0.55
    WebServlet
    0.55
     CreateTagHelper
    0.54
    $.
    0.54
     plantel
    0.52
     Giuliano
    0.51
    Trọng
    0.50
     Bioaccumulative
    0.49
    wiat
    0.48
    GeneratedValue
    0.48
    Activations Density 0.434%

    No Known Activations