© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 156877
    Prev
    Next
    INDEX
    Explanations

    week of

    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_2_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
    5
    1.30
    ه
    1.30
    is
    1.28
    a
    1.28
    ס
    1.27
    et
    1.23
    ai
    1.22
    4
    1.22
    া
    1.20
    ey
    1.19
    POSITIVE LOGITS
    ри
    1.09
    ssä
    1.04
    ON
    1.03
    ně
    0.99
    ICK
    0.96
    ИТ
    0.96
    ség
    0.96
    スの
    0.96
    ቀም
    0.96
     assaulting
    0.96
    Activations Density 0.001%

    No Known Activations