© 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. 221074
    Prev
    Next
    INDEX
    Explanations

    communication medium choice

    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
     libel
    0.33
    ਹਾ
    0.32
    媾
    0.31
     progesterone
    0.31
     prototyp
    0.31
    每天
    0.30
     ground
    0.30
     Transportation
    0.29
     airborne
    0.29
     hostility
    0.29
    POSITIVE LOGITS
    ()}
    0.28
    fyd
    0.28
    adple
    0.27
    empl
    0.27
    Me
    0.27
    quick
    0.27
    escape
    0.27
    Movies
    0.26
    Viz
    0.26
     изд
    0.26
    Activations Density 0.008%

    No Known Activations