© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 125531
    Prev
    Next
    INDEX
    Explanations

    AI Features or Beta

    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_3_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
    י
    0.80
    ۶
    0.74
    К
    0.74
    Cs
    0.72
     utiliz
    0.70
    یل
    0.70
    レ
    0.68
    Ф
    0.67
     ۔۔۔
    0.66
    LO
    0.66
    POSITIVE LOGITS
    v
    1.01
    um
    0.73
    ov
    0.71
    ون
    0.70
    en
    0.68
    يد
    0.66
    et
    0.65
    ap
    0.63
    tering
    0.63
     It
    0.63
    Activations Density 0.001%

    No Known Activations