© 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. 79369
    Prev
    Next
    INDEX
    Explanations

    modelo Version / Especial / de .

    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
    다면
    1.45
    ש
    1.37
    であった
    1.21
    י
    1.21
    ;}
    1.17
    र
    1.16
    ший
    1.16
    ですので
    1.16
     commerciali
    1.16
    つ
    1.14
    POSITIVE LOGITS
    ne
    1.79
    ag
    1.66
    k
    1.40
    it
    1.38
    l
    1.36
    '
    1.35
    ah
    1.34
    me
    1.29
    are
    1.28
    its
    1.27
    Activations Density 0.001%

    No Known Activations