© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 209358
    Prev
    Next
    INDEX
    Explanations

    surprisal and novelty

    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_25_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
    anness
    0.39
     改
    0.39
    ွေး
    0.37
     बदला
    0.35
     單
    0.35
    igkeits
    0.35
     محد
    0.34
    vey
    0.34
     quantitatively
    0.33
    述
    0.33
    POSITIVE LOGITS
     Trojans
    0.38
    !?
    0.38
    Monument
    0.37
    Poss
    0.37
    ?!?
    0.36
     Monument
    0.35
     fratern
    0.35
    ?!?!
    0.35
     Tro
    0.35
     Poss
    0.35
    Activations Density 0.008%

    No Known Activations