© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 134735
    Prev
    Next
    INDEX
    Explanations

    Erikson

    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_1_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
    ی
    1.33
    ר
    1.15
     یا
    1.11
    یف
    1.09
    یتی
    1.09
    ट
    1.07
    ั
    1.07
     ไ
    1.05
    มอง
    1.04
    یط
    1.03
    POSITIVE LOGITS
    b
    1.37
    m
    1.30
    M
    1.25
    v
    1.24
    ing
    1.23
    c
    1.18
    i
    1.17
    u
    1.17
    g
    1.17
    ká
    1.15
    Activations Density 0.000%

    No Known Activations