© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 29114
    Prev
    Next
    INDEX
    Explanations

    announcement research alternative

    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_10_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
    0.75
     progenitor
    0.72
    ose
    0.70
    og
    0.69
     artery
    0.68
     沒有
    0.67
     de
    0.65
     శరీర
    0.63
    𝙪
    0.63
    irá
    0.62
    POSITIVE LOGITS
    ﺻ
    0.67
    ל
    0.61
     Penelitian
    0.59
    ﺯ
    0.58
     Supplements
    0.57
    ﻟ
    0.57
    اویز
    0.57
     lainnya
    0.55
    ﺑ
    0.55
    Someone
    0.55
    Activations Density 0.000%

    No Known Activations