© 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. 130039
    Prev
    Next
    INDEX
    Explanations

    mortise, mortified, mortally, mortification, mortared

    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
    u
    1.53
    مو
    1.50
    н
    1.48
    that
    1.46
    िक
    1.45
    مي
    1.36
    مون
    1.33
    न
    1.31
    is
    1.29
    مط
    1.25
    POSITIVE LOGITS
    )
    1.40
     mogul
    1.25
    ),
    1.16
    '
    1.16
     =
    1.15
     can
    1.15
    \
    1.12
    ﻭ
    1.10
    );
    1.09
    K
    1.09
    Activations Density 0.011%

    No Known Activations