© 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. 90430
    Prev
    Next
    INDEX
    Explanations

    case Clair

    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
    lie
    0.74
    on
    0.72
    ljena
    0.69
    larda
    0.68
    ía
    0.67
    lut
    0.67
    _
    0.67
    ina
    0.67
    lid
    0.66
    cze
    0.64
    POSITIVE LOGITS
    ס
    0.74
    時間
    0.68
    ش
    0.68
    ส
    0.67
     Ariana
    0.67
     ajout
    0.66
    দ
    0.66
    ق
    0.65
    ג
    0.64
     incentivize
    0.64
    Activations Density 0.004%

    No Known Activations