© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 86021
    Prev
    Next
    INDEX
    Explanations

    Beatrice or because

    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_3_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
    s
    1.37
    m
    1.11
    t
    0.89
    y
    0.79
    r
    0.79
    f
    0.78
    the
    0.77
    u
    0.68
    j
    0.68
    M
    0.66
    POSITIVE LOGITS
    ב
    0.79
    ون
    0.77
    ü
    0.77
    اری
    0.76
    ות
    0.76
    :
    0.76
    :“
    0.72
    䚺
    0.72
    з
    0.70
    :”
    0.68
    Activations Density 0.000%

    No Known Activations