© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 182925
    Prev
    Next
    INDEX
    Explanations

    findings/results followed by verbs

    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_29_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
     צריך
    0.41
    ❛
    0.39
    italizationType
    0.39
    ុ
    0.39
    ставляет
    0.37
    Poker
    0.36
    㳒
    0.36
    导
    0.35
    Enough
    0.35
    щал
    0.35
    POSITIVE LOGITS
     dirt
    0.42
     collaborazione
    0.41
     collaboration
    0.41
     materna
    0.40
     SMC
    0.40
     flattened
    0.39
     space
    0.39
     coarse
    0.39
    formed
    0.38
    dirt
    0.38
    Activations Density 0.000%

    No Known Activations