© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 133768
    Prev
    Next
    INDEX
    Explanations

    actionable insights, ideas, strategies

    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_1_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
    ﺍ
    1.42
    자
    1.37
    Ա
    1.37
     PWMB
    1.31
    О
    1.30
    미
    1.28
     of
    1.27
    た
    1.27
    Ⲓ
    1.25
    いい
    1.24
    POSITIVE LOGITS
    o
    1.44
    و
    1.41
    ו
    1.40
    ell
    1.09
    ed
    1.09
    ो
    1.08
    ো
    1.02
    ede
    1.02
    durch
    1.01
    at
    1.00
    Activations Density 0.003%

    No Known Activations