© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4041
    Prev
    Next
    INDEX
    Explanations

    mentions of default settings, options, or behaviors in code or configuration contexts.

    oai_token-act-pair · gemini-2.0-flash

    default

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     default
    -2.31
    default
    -2.19
    Default
    -1.98
     Default
    -1.98
     defaults
    -1.62
     DEFAULT
    -1.60
    DEFAULT
    -1.48
    默认
    -1.48
     defaulted
    -1.34
     默认
    -1.24
    POSITIVE LOGITS
    دانشنامهٔ
    0.53
    complexType
    0.50
    windowFixed
    0.48
    داشت
    0.48
    elock
    0.47
     Wear
    0.42
    Rhestr
    0.42
    سیون
    0.42
    struzione
    0.41
    FlatAppearance
    0.41
    Activations Density 7.934%

    No Known Activations