© 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. 11258
    Prev
    Next
    INDEX
    Explanations

    dollar amounts and percentages

    oai_token-act-pair · gemini-2.0-flash

    financial figures and values

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

    numerical digits

    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
     Roskov
    -0.78
    ########.
    -0.68
    Referències
    -0.64
     autorytatywna
    -0.63
    таратура
    -0.62
    requestCode
    -0.61
    enumi
    -0.60
    Дереккөздер
    -0.60
    Cyfeiriadau
    -0.60
    elemField
    -0.60
    POSITIVE LOGITS
    AddTagHelper
    0.63
    IsContent
    0.48
    */;
    0.47
    >())
    0.46
     venons
    0.45
    $")
    0.44
     limiti
    0.44
    Right
    0.43
     }}$}
    0.43
     right
    0.42
    Activations Density 4.235%

    No Known Activations