© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 86324
    Prev
    Next
    INDEX
    Explanations

    index.php

    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_3_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
    a
    0.82
    ر
    0.61
    ه
    0.61
    h
    0.58
    ᚨ
    0.58
     Computational
    0.57
     Garnier
    0.56
    aqueous
    0.55
     выглядит
    0.55
    uities
    0.55
    POSITIVE LOGITS
    м
    1.15
    ę
    0.80
    م
    0.73
    <0x0D>
    0.72
    یت
    0.71
    </b>
    0.70
    у
    0.70
    </strong>
    0.68
     or
    0.67
    يل
    0.66
    Activations Density 0.001%

    No Known Activations