© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201868
    Prev
    Next
    INDEX
    Explanations

    casinos and resorts

    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_12_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
     Luke
    0.61
     restrain
    0.58
     Л
    0.52
     Lake
    0.52
     St
    0.51
     स्क्रिप्ट
    0.51
    St
    0.50
    let
    0.50
     വരുന്ന
    0.50
     L
    0.49
    POSITIVE LOGITS
     suasana
    0.61
    iculos
    0.53
    зва
    0.50
    ми
    0.49
    amination
    0.49
    சாமி
    0.49
    лів
    0.49
     orgánica
    0.49
     unchanged
    0.48
    щина
    0.48
    Activations Density 0.000%

    No Known Activations