© 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. 103668
    Prev
    Next
    INDEX
    Explanations

    EMPLOYEE English and Thai

    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
    ン
    1.22
    νει
    1.00
    ν
    0.98
    κι
    0.98
    μα
    0.94
    '
    0.93
    ing
    0.93
    ἀ
    0.93
    िंग
    0.90
    ły
    0.90
    POSITIVE LOGITS
    ,
    1.23
    _
    1.20
    7
    1.09
    8
    1.05
    ii
    1.00
    9
    0.99
     in
    0.98
     that
    0.93
    iii
    0.93
    dır
    0.93
    Activations Density 0.000%

    No Known Activations