© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 141969
    Prev
    Next
    INDEX
    Explanations

    been

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     still
    0.63
     Still
    0.60
    still
    0.53
     STILL
    0.53
    仍
    0.53
    Still
    0.50
     todavía
    0.50
     još
    0.48
     아직
    0.47
    まだまだ
    0.47
    POSITIVE LOGITS
    reeting
    0.39
     gehad
    0.39
     humans
    0.37
    Global
    0.37
    看过
    0.36
    entive
    0.35
    셨
    0.35
     बट
    0.35
    GLOBAL
    0.35
     Επι
    0.35
    Activations Density 0.001%

    No Known Activations