© 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. 51182
    Prev
    Next
    INDEX
    Explanations

    nullable types

    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
    ﺒ
    0.63
    КА
    0.61
    と
    0.59
    ၅
    0.59
    
    0.57
    ち
    0.57
     پارٹی
    0.56
     بالٹ
    0.56
    ﻤ
    0.55
    บ
    0.55
    POSITIVE LOGITS
    y
    0.76
    de
    0.73
    g
    0.73
    te
    0.69
    I
    0.69
    en
    0.68
    ir
    0.68
    il
    0.66
    ни
    0.65
    anians
    0.65
    Activations Density 0.011%

    No Known Activations