© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 31465
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs and common actions

    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_7_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
    \
    0.30
    0.29
     a
    0.29
     to
    0.26
    '
    0.26
    ש
    0.26
     will
    0.24
     is
    0.24
    a
    0.22
    y
    0.22
    POSITIVE LOGITS
    .”.
    0.22
    他的
    0.21
    নন্দ
    0.21
     vati
    0.20
    ҷ
    0.20
    怖い
    0.20
    が大きい
    0.20
    리와
    0.19
     فونبټ
    0.19
     Süden
    0.19
    Activations Density 0.007%

    No Known Activations