© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 105564
    Prev
    Next
    INDEX
    Explanations

    section titled situation

    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
    1.22
    orems
    1.20
    ă
    1.18
    s
    1.14
    기
    1.14
    م
    1.13
     time
    1.09
    两
    1.07
    ا
    0.98
     more
    0.98
    POSITIVE LOGITS
    ;')
    1.05
    COURSE
    1.04
    f
    1.01
    fulfill
    0.99
    ປະກອບ
    0.99
    factorial
    0.96
    preserve
    0.95
    promote
    0.94
    SerialNumber
    0.93
    vori
    0.93
    Activations Density 0.002%

    No Known Activations