© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32016
    Prev
    Next
    INDEX
    Explanations

    mixing gently

    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_31_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
    ABCDEFGHIJKLMNOP
    0.41
     reshaping
    0.39
    融
    0.39
     timing
    0.38
     համ
    0.38
     rivulet
    0.37
     delay
    0.36
    刪
    0.36
     adjacency
    0.35
     முன்னர்
    0.35
    POSITIVE LOGITS
    DLL
    0.40
    álov
    0.38
    nä
    0.38
    Nä
    0.37
     शोर
    0.36
    Restore
    0.36
    CONFLICT
    0.36
    crever
    0.35
     প্রিয়
    0.35
    ќ
    0.35
    Activations Density 0.031%

    No Known Activations