© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 195101
    Prev
    Next
    INDEX
    Explanations

    latte art or pro devices

    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_15_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
     pericol
    0.53
     glomerular
    0.51
     injunctive
    0.49
     रोचक
    0.49
     угле
    0.48
    amente
    0.48
     alve
    0.48
    凿
    0.48
     teak
    0.48
     دھ
    0.47
    POSITIVE LOGITS
    ၾ
    0.50
    ،
    0.48
    Ernest
    0.46
    Luke
    0.44
    currency
    0.43
    יר
    0.42
    Congress
    0.42
    داء
    0.42
    amsung
    0.42
    هور
    0.42
    Activations Density 0.000%

    No Known Activations