© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 122657
    Prev
    Next
    INDEX
    Explanations

    Renée Brown

    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
    ام
    0.61
    umum
    0.57
     homely
    0.55
    y
    0.55
    modeling
    0.54
    дини
    0.54
     потрі
    0.54
    lenül
    0.54
    drawable
    0.53
    மையான
    0.53
    POSITIVE LOGITS
    ক
    0.66
     médicaments
    0.66
     medicamentos
    0.65
    ella
    0.65
    ão
    0.64
    ING
    0.63
     conflictos
    0.63
    In
    0.61
     réseaux
    0.61
    .,
    0.61
    Activations Density 0.000%

    No Known Activations