© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 53470
    Prev
    Next
    INDEX
    Explanations

    <

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
    verick
    0.41
     '.$
    0.40
     움직
    0.40
    ariously
    0.38
    '.$
    0.38
    ²',
    0.38
     খেয়ে
    0.38
     молоды
    0.37
     గుర్తు
    0.37
    ¹,
    0.37
    POSITIVE LOGITS
     indexing
    0.40
     raisons
    0.39
     termini
    0.39
     grammes
    0.39
     indexed
    0.37
    eln
    0.36
     reasoning
    0.36
     இயக்கு
    0.36
    ่าย
    0.36
     grammar
    0.36
    Activations Density 0.001%

    No Known Activations