© 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. 90560
    Prev
    Next
    INDEX
    Explanations

    complete the task

    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
    ﺕ
    0.78
    '
    0.71
    ﻥ
    0.71
    t
    0.70
    inį
    0.66
    selves
    0.64
     reorgan
    0.61
    g
    0.61
     enunciado
    0.59
    hoes
    0.59
    POSITIVE LOGITS
    };
    0.76
     którym
    0.71
    С
    0.67
     ș
    0.67
    ING
    0.66
     niya
    0.65
    হইবে
    0.65
     hvilket
    0.65
     неё
    0.64
     genieten
    0.64
    Activations Density 0.001%

    No Known Activations