© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43298
    Prev
    Next
    INDEX
    Explanations

    CV or resume

    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_22_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
    apha
    0.23
     jeśli
    0.22
     alınd
    0.21
    e
    0.20
     Secondary
    0.20
     Kommun
    0.20
     Or
    0.19
     noticeable
    0.19
     Як
    0.19
     spes
    0.19
    POSITIVE LOGITS
    سط
    0.25
    рте
    0.23
    rosse
    0.23
    cession
    0.22
    橄
    0.22
    髯
    0.22
    }^{
    0.22
    fZ
    0.22
    YNAM
    0.22
    وجوان
    0.21
    Activations Density 0.010%

    No Known Activations