© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 228277
    Prev
    Next
    INDEX
    Explanations

    in and out

    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_6_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
    ल
    1.30
    р
    1.18
    ל
    1.18
     pequenas
    1.08
    ル
    1.05
    са
    1.05
    の結果
    0.99
    َی
    0.98
    લ
    0.98
    ви
    0.96
    POSITIVE LOGITS
    st
    1.26
    t
    1.25
    c
    1.24
    ali
    1.20
    *
    1.19
    h
    1.09
    com
    1.07
    r
    1.07
    ?
    1.06
    !
    1.04
    Activations Density 0.000%

    No Known Activations