© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83853
    Prev
    Next
    INDEX
    Explanations

    beschränkungen / descripciones

    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_0_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
    ти
    2.03
    U
    1.53
    W
    1.43
    ू
    1.36
    B
    1.34
    O
    1.34
    श
    1.29
    ne
    1.27
    у
    1.26
    ター
    1.22
    POSITIVE LOGITS
     are
    1.45
     постро
    1.41
    ра
    1.39
     efficaces
    1.38
     añad
    1.33
     incendi
    1.32
     механиз
    1.30
    য়া
    1.29
    。
    1.28
     обши
    1.27
    Activations Density 0.000%

    No Known Activations