© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 200858
    Prev
    Next
    INDEX
    Explanations

    say biases

    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_46_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
     input
    0.43
     recursion
    0.41
     सतत
    0.39
    input
    0.39
    ousse
    0.39
     cią
    0.38
    interpre
    0.38
    복
    0.37
     media
    0.36
    मीडिया
    0.36
    POSITIVE LOGITS
    rante
    0.39
    rantes
    0.38
     Implicit
    0.38
    Embedded
    0.37
    voirs
    0.37
     hacks
    0.37
     Remain
    0.37
     gender
    0.36
    anting
    0.36
    Implicit
    0.36
    Activations Density 0.006%

    No Known Activations