© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 165889
    Prev
    Next
    INDEX
    Explanations

    best and positive forecasts

    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_31_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
     rá
    0.38
    වුන්
    0.36
    极端
    0.36
    gré
    0.36
    лиш
    0.35
    未必
    0.35
    극
    0.34
    ιο
    0.34
     qal
    0.34
     rpm
    0.34
    POSITIVE LOGITS
     INCRE
    0.42
     explosive
    0.40
     incre
    0.40
     exciting
    0.40
     আঙ্গ
    0.40
     modele
    0.39
     prosperous
    0.37
     Modelle
    0.37
     stagione
    0.36
     exuberant
    0.36
    Activations Density 0.019%

    No Known Activations