© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35293
    Prev
    Next
    INDEX
    Explanations

    is a/an

    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_11_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
    i
    0.69
     markt
    0.67
    mess
    0.64
     obligación
    0.63
     Nieto
    0.63
     respuestas
    0.62
    iencia
    0.62
    جين
    0.62
     دونك
    0.61
     finca
    0.60
    POSITIVE LOGITS
    isations
    0.67
    is
    0.64
     up
    0.63
    tta
    0.61
    ใช้
    0.59
    /
    0.59
     be
    0.59
    yp
    0.59
    ขึ้น
    0.59
    ている
    0.57
    Activations Density 0.011%

    No Known Activations