© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103986
    Prev
    Next
    INDEX
    Explanations

    NEVER followed by a verb

    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_1_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
    ன்
    1.18
     that
    1.02
    िक
    1.02
    و
    0.90
     shrines
    0.89
    w
    0.89
    มัน
    0.89
    ש
    0.87
    י
    0.86
     membres
    0.84
    POSITIVE LOGITS
    on
    1.37
    Equation
    1.16
    December
    1.07
    April
    1.06
    The
    1.02
    the
    0.99
    ght
    0.99
    การ
    0.96
    行う
    0.96
    Method
    0.95
    Activations Density 0.000%

    No Known Activations