© 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. 14137
    Prev
    Next
    INDEX
    Explanations

    iced drinks and coffee

    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
    afood
    0.47
     Kumb
    0.46
     छा
    0.44
    Ā
    0.43
    ците
    0.43
     Saal
    0.42
    Dirt
    0.41
    aadhar
    0.41
    嗳
    0.41
    Ethn
    0.40
    POSITIVE LOGITS
    зиден
    0.57
     हों
    0.54
     allá
    0.53
     needn
    0.51
     remedies
    0.50
     pessoais
    0.48
     próprios
    0.47
    rooms
    0.47
     hué
    0.47
    cer
    0.46
    Activations Density 0.003%

    No Known Activations