© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 88411
    Prev
    Next
    INDEX
    Explanations

    hundreds

    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_60_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
     million
    2.83
     Million
    2.34
     billion
    2.31
    million
    2.30
    万
    2.27
    萬
    2.14
    Million
    2.11
    billion
    1.85
     trillion
    1.84
     万
    1.80
    POSITIVE LOGITS
     सैकड़ों
    0.44
     hundreds
    0.43
    Hundreds
    0.41
    opis
    0.38
    offe
    0.38
     Hundreds
    0.38
    Bigg
    0.35
    Lời
    0.35
    វិធី
    0.35
    DataLoader
    0.34
    Activations Density 0.016%

    No Known Activations