© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 136002
    Prev
    Next
    INDEX
    Explanations

    snow and cloud conditions

    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_37_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
     streaming
    0.41
     eligibility
    0.41
     Eligibility
    0.40
    Streaming
    0.39
     categorías
    0.39
    ﻘ
    0.39
     tablas
    0.38
     comprehensively
    0.37
     verticales
    0.37
     로그인
    0.37
    POSITIVE LOGITS
    atele
    0.37
     Bond
    0.37
     quenched
    0.37
     వ్యవస్థ
    0.37
     Owners
    0.36
    விய
    0.36
    assembly
    0.36
    asking
    0.36
    㝌
    0.35
    Markup
    0.35
    Activations Density 0.001%

    No Known Activations