© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 155478
    Prev
    Next
    INDEX
    Explanations

    change

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
     달라
    0.44
     değiştir
    0.42
     바꾸
    0.37
     specialise
    0.37
     바꿔
    0.37
    食
    0.36
     et
    0.35
     monog
    0.35
    рень
    0.35
    விக்க
    0.34
    POSITIVE LOGITS
    変
    1.82
     変
    1.34
    變
    1.17
    变
    1.07
    に変
    1.02
     변
    1.01
     biến
    0.95
     вари
    0.94
     Var
    0.92
    변
    0.91
    Activations Density 0.006%

    No Known Activations