© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 100546
    Prev
    Next
    INDEX
    Explanations

    seaweed extract

    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_16_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
    sports
    0.57
     ശേഷം
    0.55
     Retrie
    0.55
     баскет
    0.54
    мо
    0.52
     ۴
    0.51
     هەر
    0.50
    ๗
    0.50
     والی
    0.49
     occhi
    0.49
    POSITIVE LOGITS
    ː
    0.57
     estancia
    0.54
     lengua
    0.53
    enang
    0.50
    ﻟ
    0.50
     wages
    0.50
    ｌ
    0.49
     woodwork
    0.49
     Puente
    0.49
    Beans
    0.48
    Activations Density 0.002%

    No Known Activations