© 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. 49483
    Prev
    Next
    INDEX
    Explanations

    (a) or (b)

    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
     alternative
    0.31
     zumindest
    0.30
     Brook
    0.30
     ample
    0.30
     Berth
    0.30
     другого
    0.29
     Timer
    0.29
    長
    0.29
     Transitions
    0.29
     بط
    0.29
    POSITIVE LOGITS
    Requested
    0.39
    ptt
    0.34
    pO
    0.34
    ktx
    0.34
    residential
    0.33
     गर्मियों
    0.33
    Creat
    0.33
    ConfigRequest
    0.33
    Departure
    0.33
    খ্যার
    0.32
    Activations Density 0.000%

    No Known Activations