© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157749
    Prev
    Next
    INDEX
    Explanations

    Kamehameha, aha

    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_2_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
    ע
    1.37
    ת
    1.32
    ל
    1.29
    c
    1.27
    ח
    1.23
    ت
    1.17
    স
    1.16
    ו
    1.16
    на
    1.13
    אים
    1.07
    POSITIVE LOGITS
    0
    1.52
     are
    1.27
     be
    1.20
    1
    1.18
     for
    1.14
     a
    1.13
     μεγάλη
    1.05
    ão
    1.01
    íme
    1.01
    patial
    0.98
    Activations Density 0.000%

    No Known Activations