© 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. 87500
    Prev
    Next
    INDEX
    Explanations

    basis points

    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
    ث
    0.66
    I
    0.64
    人
    0.61
    shu
    0.60
    sd
    0.60
    سه
    0.57
    sa
    0.57
    th
    0.56
    ds
    0.55
    datab
    0.55
    POSITIVE LOGITS
    ান
    0.72
    ﻟ
    0.68
    ’),
    0.63
    ﺢ
    0.61
    ’?
    0.59
     වශ
    0.59
    ﻜ
    0.58
    ิน
    0.57
    ’
    0.57
    ﻠ
    0.55
    Activations Density 0.000%

    No Known Activations