© 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. 35226
    Prev
    Next
    INDEX
    Explanations

    chapter or episode followed by a number or "One"

    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
     rupani
    0.30
     overcrow
    0.29
     ב
    0.29
    CTION
    0.29
     amacı
    0.29
     ﺍ
    0.29
     improve
    0.28
     attenuate
    0.28
     tokamaks
    0.28
    ﻙ
    0.28
    POSITIVE LOGITS
    iken
    0.30
    ín
    0.29
    <0xA7>
    0.29
    <0xA0>
    0.28
    ium
    0.27
    <0xB9>
    0.27
    aks
    0.27
    <0xBF>
    0.26
    ian
    0.26
    <0xAF>
    0.25
    Activations Density 0.015%

    No Known Activations