© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 31204
    Prev
    Next
    INDEX
    Explanations

    demise

    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_7_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
     to
    0.30
     with
    0.29
     that
    0.27
     on
    0.27
    L
    0.26
    ain
    0.26
    ado
    0.25
     at
    0.25
    becue
    0.25
     of
    0.25
    POSITIVE LOGITS
    ও
    0.40
    在
    0.35
    ה
    0.35
    و
    0.33
    ка
    0.32
     في
    0.31
    ك
    0.31
    もら
    0.31
    ла
    0.30
    ро
    0.28
    Activations Density 0.002%

    No Known Activations