© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 201326
    Prev
    Next
    INDEX
    Explanations

    rightmost

    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_6_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
    j
    1.21
    с
    1.15
    ı
    1.13
    س
    1.11
    ll
    1.00
    $,
    0.97
    ng
    0.97
    li
    0.92
    í
    0.92
    হ
    0.89
    POSITIVE LOGITS
    ایی
    0.91
     actuation
    0.87
     cabs
    0.86
     chinos
    0.86
     endoplasmic
    0.86
     prepayment
    0.84
    ونی
    0.83
     públicos
    0.82
     primates
    0.80
     locomotor
    0.80
    Activations Density 0.000%

    No Known Activations