© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158905
    Prev
    Next
    INDEX
    Explanations

    hammer

    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_2_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
    ,
    1.48
    /
    1.46
     in
    1.30
    ;
    1.18
    +
    1.16
    :
    1.16
     styl
    1.13
    ?
    1.04
     reorgan
    1.02
     oxid
    1.01
    POSITIVE LOGITS
    u
    1.63
    ar
    1.34
    ا
    1.34
    en
    1.23
    ی
    1.23
    یی
    1.22
    arai
    1.17
    ri
    1.16
    ab
    1.16
    ا۔
    1.15
    Activations Density 0.001%

    No Known Activations