© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157633
    Prev
    Next
    INDEX
    Explanations

    Mati, Mami, Matina, Satiety, Mane

    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_2_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
    า
    1.89
    at
    1.75
    на
    1.63
    ي
    1.53
    ا
    1.37
    يها
    1.25
    ap
    1.20
    ל
    1.20
    ta
    1.16
    يلي
    1.15
    POSITIVE LOGITS
     dismay
    1.30
    );
    1.28
    ，
    1.26
    ،
    1.23
    は
    1.12
    :
    1.10
     $\
    1.05
     :
    1.05
    =\
    1.02
    ;
    1.01
    Activations Density 0.008%

    No Known Activations