© 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. 88409
    Prev
    Next
    INDEX
    Explanations

    Like

    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
     all
    0.91
     most
    0.84
    most
    0.71
     Most
    0.68
    Most
    0.64
     a
    0.61
     many
    0.56
     All
    0.56
    all
    0.55
    MOST
    0.48
    POSITIVE LOGITS
    .**
    0.39
     quelques
    0.38
     determinado
    0.38
     حتی
    0.38
     थोड़ी
    0.38
     کچھ
    0.37
     nekaj
    0.37
     不同
    0.37
    ﮐ
    0.37
     pleno
    0.37
    Activations Density 0.002%

    No Known Activations