© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79446
    Prev
    Next
    INDEX
    Explanations

    http get expedia

    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_0_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
     It
    1.56
    c
    1.40
    k
    1.34
     If
    1.30
    p
    1.30
    ty
    1.20
     Applies
    1.18
    ten
    1.16
    v
    1.16
    ts
    1.11
    POSITIVE LOGITS
    는
    2.30
    ת
    2.14
    ة
    2.05
    ა
    2.02
    트
    2.02
    ي
    1.98
    ม
    1.87
     in
    1.86
    ה
    1.82
    は
    1.81
    Activations Density 0.000%

    No Known Activations