© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 211545
    Prev
    Next
    INDEX
    Explanations

    weeks or nights

    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_20_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
     week
    0.52
    ेलकम
    0.50
     ہفت
    0.49
    酐
    0.47
     hardworking
    0.47
     incrementar
    0.47
     WEEK
    0.46
     alguns
    0.45
    ຯ
    0.45
     fortnight
    0.44
    POSITIVE LOGITS
    patients
    0.46
    =
    0.45
     пациента
    0.43
     zurück
    0.43
    patient
    0.42
    kennt
    0.41
    */
    0.41
    Medico
    0.41
    ra
    0.40
    ga
    0.40
    Activations Density 0.000%

    No Known Activations