© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89325
    Prev
    Next
    INDEX
    Explanations

    how might

    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
    ’
    0.83
    ב
    0.79
    0
    0.73
    in
    0.70
    d
    0.70
    The
    0.69
    es
    0.67
    ات
    0.66
    ת
    0.64
    מ
    0.63
    POSITIVE LOGITS
     can
    0.72
     (
    0.72
     verwend
    0.71
     are
    0.70
     keing
    0.68
    ियल
    0.61
     },
    0.61
     llev
    0.60
     }-\
    0.60
     coordin
    0.59
    Activations Density 0.002%

    No Known Activations