© 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. 141842
    Prev
    Next
    INDEX
    Explanations

    "+" symbol and related operators

    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
    a
    1.83
    in
    1.52
    ה
    1.51
    ।
    1.45
    न
    1.41
    to
    1.38
    o
    1.35
    CTION
    1.31
    מ
    1.27
    н
    1.23
    POSITIVE LOGITS
    த்தில்
    1.39
    ים
    1.36
    తో
    1.27
    ς
    1.25
     Τ
    1.22
    ానికి
    1.21
    ak
    1.16
    ناک
    1.15
    檚
    1.13
    中
    1.13
    Activations Density 0.000%

    No Known Activations