© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 207297
    Prev
    Next
    INDEX
    Explanations

    cardioid, sensitivity, discrimination, directional

    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_19_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
     правильно
    0.50
    Ⴎ
    0.46
     MAKING
    0.45
    কারী
    0.44
     жан
    0.43
    ucaly
    0.43
     eukaryotes
    0.43
    䍜
    0.43
     ऐ
    0.42
     různ
    0.42
    POSITIVE LOGITS
     tasa
    0.46
    وزی
    0.44
     ves
    0.43
     conciencia
    0.43
     receding
    0.43
     pago
    0.43
    gon
    0.42
     shield
    0.41
    resistance
    0.41
     call
    0.40
    Activations Density 0.001%

    No Known Activations