© 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. 31085
    Prev
    Next
    INDEX
    Explanations

    import util and io

    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
    דיה
    0.38
    adeso
    0.37
    >−</
    0.37
    Codes
    0.37
    mA
    0.37
    }}^{
    0.36
     sevi
    0.36
    lichess
    0.36
    ać
    0.36
    āda
    0.36
    POSITIVE LOGITS
     Houston
    0.43
     Victim
    0.40
     Slot
    0.40
     Taken
    0.39
     Emotional
    0.38
     Asking
    0.38
     Victims
    0.38
    遐
    0.38
     Process
    0.38
     Showing
    0.38
    Activations Density 0.000%

    No Known Activations