© 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. 6208
    Prev
    Next
    INDEX
    Explanations

    multi-digit numbers

    oai_token-act-pair · gemini-2.0-flash

    programming-related keywords

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

    mathematical sequences

    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
    mybatisplus
    -0.54
    photobucket
    -0.53
    脚注の使い方
    -0.53
     lägga
    -0.52
     ([]
    -0.52
    quées
    -0.50
    ült
    -0.49
    selaer
    -0.48
    θηκαν
    -0.48
    balleur
    -0.47
    POSITIVE LOGITS
    InjectAttribute
    0.72
    WebControls
    0.63
    DeleteBehavior
    0.61
     Italijanski
    0.57
    LookAnd
    0.57
    parsedMessage
    0.54
    uxxxx
    0.54
    RTLD
    0.54
    randomUUID
    0.54
    aarrggbb
    0.53
    Activations Density 12.792%

    No Known Activations