© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 141869
    Prev
    Next
    INDEX
    Explanations

    digits

    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_46_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
     Buss
    0.39
     out
    0.38
     अम
    0.35
    跟我
    0.35
    ⵎ
    0.34
    дем
    0.33
    United
    0.33
    นัก
    0.33
    OutOf
    0.33
    bodyA
    0.32
    POSITIVE LOGITS
     subfamily
    0.38
    adone
    0.37
    ){}^
    0.37
    awab
    0.36
     [%
    0.36
     দশ
    0.36
     sacrament
    0.35
    十
    0.35
    綏
    0.35
    }|^{
    0.35
    Activations Density 0.004%

    No Known Activations