© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 210727
    Prev
    Next
    INDEX
    Explanations

    till tomorrow

    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_5_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
    ع
    1.71
    ق
    1.39
    도
    1.37
     در
    1.28
    علم
    1.25
    보
    1.25
    bagian
    1.23
    ја
    1.20
    ح
    1.20
    在
    1.17
    POSITIVE LOGITS
    :
    1.26
    in
    1.19
    et
    1.13
    ன்
    1.05
    d
    1.05
    al
    1.04
    inizi
    1.02
    er
    0.97
     significantly
    0.96
     and
    0.96
    Activations Density 0.001%

    No Known Activations