© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13814
    Prev
    Next
    INDEX
    Explanations

    methodology and conventions

    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_13_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
    }'
    0.34
    ]_
    0.33
    uera
    0.33
    ನಲ್ಲಿ
    0.33
     verdens
    0.32
    $\--
    0.32
    মন্ত্রী
    0.32
    जानिए
    0.32
    朤
    0.32
    inggi
    0.31
    POSITIVE LOGITS
     پ
    0.40
     p
    0.37
    ᴅ
    0.35
     प
    0.35
    Ｇ
    0.34
    ደበ
    0.34
    同じ
    0.33
     assuming
    0.33
    噓
    0.32
     same
    0.32
    Activations Density 0.273%

    No Known Activations