© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 132872
    Prev
    Next
    INDEX
    Explanations

    drumroll please

    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_1_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
     in
    1.19
    ς
    1.17
    s
    1.05
    ;
    1.03
    res
    0.96
    ों
    0.86
    ला
    0.86
    ذ
    0.86
    ων
    0.85
    chh
    0.84
    POSITIVE LOGITS
    p
    1.26
    า
    1.10
    𝙖
    1.05
     a
    1.04
    המ
    1.04
    𝐚
    1.04
    𝕒
    1.02
     và
    1.02
    B
    1.02
    𝗮
    1.02
    Activations Density 0.003%

    No Known Activations