© 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. 92755
    Prev
    Next
    INDEX
    Explanations

    in

    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
     јо
    0.38
     године
    0.38
    օ
    0.38
    谒
    0.38
    ци
    0.36
     vuos
    0.36
    𝐞
    0.36
    ExpireTime
    0.35
     између
    0.35
    ­
    0.35
    POSITIVE LOGITS
    1
    0.80
     Nov
    0.64
     Feb
    0.61
    2
    0.61
    5
    0.60
     Sept
    0.60
    4
    0.59
    Oct
    0.57
     Oct
    0.56
    6
    0.55
    Activations Density 0.003%

    No Known Activations