© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 163676
    Prev
    Next
    INDEX
    Explanations

    secret word or passphrase

    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_13_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
    ल
    0.28
    苃
    0.28
    \%)
    0.26
    中
    0.26
    त
    0.26
    记得
    0.25
    द
    0.25
    Leader
    0.25
    л
    0.25
    जामा
    0.24
    POSITIVE LOGITS
    ino
    0.33
     verbo
    0.29
    og
    0.27
    ale
    0.27
     could
    0.25
     dello
    0.25
    辈子
    0.25
     qualsiasi
    0.25
    <0x9D>
    0.24
    ate
    0.24
    Activations Density 0.010%

    No Known Activations