© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45542
    Prev
    Next
    INDEX
    Explanations

    list items or instructions

    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_22_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
     bruta
    0.38
    überkü
    0.38
    鷲
    0.38
    ganggu
    0.38
    メガ
    0.38
     Донец
    0.38
    राकी
    0.37
    טא
    0.37
    百万
    0.37
    Meteor
    0.37
    POSITIVE LOGITS
    だから
    0.39
    任
    0.38
     Genre
    0.38
    PREFERRED
    0.37
     Match
    0.36
     Arrays
    0.36
     practicable
    0.35
    라도
    0.35
     நின்று
    0.35
     pleased
    0.35
    Activations Density 0.006%

    No Known Activations