© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9464
    Prev
    Next
    INDEX
    Explanations

    design thinking

    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_13_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
     destrucción
    0.47
     destroying
    0.47
    тик
    0.46
     destroys
    0.44
     مانند
    0.43
    </b>
    0.43
     پیچ
    0.43
    猴
    0.43
    گه
    0.43
    மர
    0.42
    POSITIVE LOGITS
     ISNI
    0.54
     Seventh
    0.49
     Ấn
    0.48
     Jeans
    0.47
    갚
    0.46
     അമ്മ
    0.45
    jeni
    0.45
    𝟕
    0.45
     Oke
    0.44
    niejs
    0.44
    Activations Density 0.003%

    No Known Activations