© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 79457
    Prev
    Next
    INDEX
    Explanations

    preferable alternatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    羢
    0.33
     Ways
    0.33
     glTex
    0.32
     هفت
    0.31
    стема
    0.30
    やかに
    0.30
     calcareous
    0.30
    磋
    0.30
    체를
    0.29
    qrcode
    0.29
    POSITIVE LOGITS
    sov
    0.32
     fuelled
    0.31
     উচ্ছ
    0.30
     Interview
    0.30
    سٹر
    0.30
    せる
    0.29
    jük
    0.29
    lit
    0.28
    (''
    0.28
    played
    0.28
    Activations Density 0.012%

    No Known Activations