© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257907
    Prev
    Next
    INDEX
    Explanations

    saturation, volatility, metallic, magnitude, time, blue

    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_22_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
     מספר
    0.39
     číslo
    0.38
    CBS
    0.38
    善良
    0.36
    '>");
    0.35
     ভারসাম
    0.34
    );">
    0.34
    や
    0.34
     ಅಥವಾ
    0.33
    国民
    0.33
    POSITIVE LOGITS
    umes
    0.41
    oderma
    0.40
     death
    0.36
     สู
    0.36
    illions
    0.35
    varian
    0.35
    Tem
    0.35
     обучения
    0.35
     continuum
    0.35
    vim
    0.35
    Activations Density 0.021%

    No Known Activations