© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214379
    Prev
    Next
    INDEX
    Explanations

    gazes or gazpacho

    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_5_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
     I
    1.47
    .
    1.41
    ut
    1.31
    1
    1.24
     tokamak
    1.14
    ain
    1.10
    ank
    1.10
    ↵
    1.06
    ,
    1.06
    ...
    1.04
    POSITIVE LOGITS
    ى
    1.28
    می
    1.27
    것
    1.26
    ிய
    1.24
    پ
    1.23
    ли
    1.20
    အ
    1.15
    ர்கள்
    1.13
    ин
    1.13
    사
    1.13
    Activations Density 0.000%

    No Known Activations