© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 86613
    Prev
    Next
    INDEX
    Explanations

    code structure numbers

    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_3_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
    aaa
    0.61
    ת
    0.60
    ﻪ
    0.60
    ן
    0.59
    ᱮ
    0.59
     ofrec
    0.58
    و
    0.58
    ம்
    0.58
    aaaa
    0.57
    Aa
    0.55
    POSITIVE LOGITS
    在
    0.82
     in
    0.80
    ט
    0.80
    ه
    0.70
     در
    0.70
    )。
    0.70
    ру
    0.69
    اک
    0.66
    ।’
    0.63
    یک
    0.63
    Activations Density 0.001%

    No Known Activations