© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 52580
    Prev
    Next
    INDEX
    Explanations

    ends with

    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_30_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
     확률
    0.38
     forfe
    0.37
    陆续
    0.36
     защото
    0.35
     фору
    0.35
    塵
    0.35
     скоро
    0.35
     Doppio
    0.35
    런
    0.35
    一项
    0.35
    POSITIVE LOGITS
    ins
    0.40
    emplates
    0.39
     &'
    0.37
    atau
    0.37
    वाइड
    0.36
    neat
    0.36
    equals
    0.35
    thick
    0.34
    atih
    0.34
    endswith
    0.34
    Activations Density 0.002%

    No Known Activations