© 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. 6965
    Prev
    Next
    INDEX
    Explanations

    code snippets using non-English characters

    oai_token-act-pair · gemini-2.0-flash

    words related to strings in programming or specific string manipulations

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

    foreign languages

    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
    gdala
    -0.60
    kháu
    -0.54
    влении
    -0.52
    ném
    -0.51
    ждении
    -0.50
    énagement
    -0.50
    hoeddwyd
    -0.50
    جغرافيا
    -0.49
     endwhile
    -0.48
     विश्वसनीयता
    -0.48
    POSITIVE LOGITS
    に
    0.68
    шению
    0.65
    ಗೆ
    0.64
    ylle
    0.62
    жению
    0.61
    tahui
    0.61
    влению
    0.60
    nak
    0.60
     に
    0.59
    ことに
    0.59
    Activations Density 0.116%

    No Known Activations