© 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. 31148
    Prev
    Next
    INDEX
    Explanations

    between layers and sessions

    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
    ב
    0.35
    פים
    0.31
    ار
    0.30
     follicles
    0.30
    এবং
    0.29
     kurze
    0.28
     et
    0.28
    ال
    0.28
    在
    0.28
    ין
    0.27
    POSITIVE LOGITS
    1
    0.28
    禦
    0.27
    ны
    0.25
    ாதார
    0.25
     noastră
    0.25
    án
    0.24
    ta
    0.24
    ály
    0.24
    >.
    0.23
    the
    0.23
    Activations Density 0.005%

    No Known Activations