© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 53122
    Prev
    Next
    INDEX
    Explanations

    base64 encoding

    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_30_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
    잖아요
    0.33
     হলেন
    0.31
    পৃথ
    0.30
    ritten
    0.30
    DanhMucSP
    0.30
    шень
    0.29
    ޝ
    0.29
     हिस्
    0.28
     tomon
    0.28
    TiO
    0.27
    POSITIVE LOGITS
     스토리
    0.28
    buildCommand
    0.27
     Keyboard
    0.27
    (+
    0.26
     Panic
    0.25
     Builder
    0.25
     panic
    0.25
     Nike
    0.25
    {%
    0.24
     ബന്ധ
    0.24
    Activations Density 0.001%

    No Known Activations