© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7747
    Prev
    Next
    INDEX
    Explanations

    angle bracket markup and escaped characters in computer code or scientific writing

    oai_token-act-pair · gemini-2.0-flash

    programming syntax elements

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

    technical code/language

    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
    发表于
    -0.51
    esez
    -0.40
     bago
    -0.40
     Lexikon
    -0.38
    —(
    -0.38
     stanovnika
    -0.38
     marina
    -0.36
    িতে
    -0.36
     doble
    -0.36
     Eindhoven
    -0.34
    POSITIVE LOGITS
    WithIOException
    0.89
    ThroughAttribute
    0.87
    __':
    0.79
    AsUp
    0.77
     propOrder
    0.73
     Wikimedijinoj
    0.72
    enumi
    0.71
    findpost
    0.68
    resave
    0.66
    LayoutConstraint
    0.66
    Activations Density 0.210%

    No Known Activations