© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62208
    Prev
    Next
    INDEX
    Explanations

    signs of symptoms

    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_11_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
    لي
    0.69
    铅
    0.58
    ፈል
    0.56
    鉛
    0.53
    𒆤
    0.53
    ляю
    0.52
    ﻈ
    0.52
    SDLCheck
    0.50
    昶
    0.50
    純
    0.49
    POSITIVE LOGITS
    n
    0.86
    al
    0.71
    re
    0.70
    st
    0.66
    isation
    0.66
    h
    0.65
    v
    0.64
    y
    0.63
    au
    0.62
    ay
    0.61
    Activations Density 0.000%

    No Known Activations