© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 31597
    Prev
    Next
    INDEX
    Explanations

    not, negation

    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_40_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
     *);
    0.38
    hecy
    0.37
    рее
    0.37
    سة
    0.36
     বয়সী
    0.36
    ມັນ
    0.36
    ﻞ
    0.36
     ہاں
    0.35
     ነ
    0.35
     žiad
    0.34
    POSITIVE LOGITS
     not
    1.66
     NOT
    1.42
    not
    1.38
     Not
    1.38
    Not
    1.37
     bukan
    1.29
    NOT
    1.26
     ليس
    1.23
     nicht
    1.23
    不是
    1.18
    Activations Density 0.047%

    No Known Activations