© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 87653
    Prev
    Next
    INDEX
    Explanations

    pages loaded

    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_23_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
    制
    0.42
     spitting
    0.41
    Unique
    0.38
    রণ
    0.38
    api
    0.37
    στ
    0.36
    蒲
    0.36
    meer
    0.35
    Evil
    0.35
    Verse
    0.35
    POSITIVE LOGITS
     または
    0.53
     específicamente
    0.53
    鷳
    0.50
     данной
    0.49
     productores
    0.48
     seleccionado
    0.48
     stockholders
    0.46
    ುತ್ತಿರುವ
    0.46
     indicato
    0.46
     ব্যবস্থাপনা
    0.46
    Activations Density 0.000%

    No Known Activations