© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11919
    Prev
    Next
    INDEX
    Explanations

    code block delimiters and separators.

    oai_token-act-pair · gemini-2.0-flash

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    jem
    -0.35
     Yad
    -0.33
    AsUp
    -0.32
    lem
    -0.32
     inbox
    -0.31
    tır
    -0.30
    providedIn
    -0.30
    ướ
    -0.30
    s
    -0.29
     fırs
    -0.28
    POSITIVE LOGITS
    TagMode
    0.80
     autorytatywna
    0.76
     referenties
    0.75
    المكان
    0.70
    rungsseite
    0.69
    //{
    0.69
    請繼續往下閱讀
    0.68
     Namens
    0.67
    \{\\
    0.66
    Controllo
    0.65
    Activations Density 3.978%

    No Known Activations