© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89576
    Prev
    Next
    INDEX
    Explanations

    Fixed Assets

    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
    an
    0.59
    ER
    0.54
    л
    0.53
    이라는
    0.52
    AN
    0.50
    이나
    0.50
    asjon
    0.50
    (
    0.49
    э
    0.49
    Seit
    0.48
    POSITIVE LOGITS
    sh
    0.75
     judíos
    0.73
    )$.
    0.73
     humanos
    0.72
     philippines
    0.72
    </h3>
    0.72
     diarios
    0.71
     Ա
    0.70
     invitados
    0.69
     policías
    0.69
    Activations Density 0.001%

    No Known Activations