© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 49574
    Prev
    Next
    INDEX
    Explanations

    categorized information

    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_31_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
    稒
    0.24
     DispatchQueue
    0.24
    和小
    0.23
     tie
    0.23
     indiquer
    0.23
    捂
    0.23
    可以说
    0.22
    ્રો
    0.22
    包
    0.22
    以及
    0.22
    POSITIVE LOGITS
    trasound
    0.24
    nolds
    0.23
     incense
    0.23
     Tucker
    0.23
     Katz
    0.23
    ersk
    0.23
    ന്യ
    0.23
    했고
    0.23
     pws
    0.22
    ovirus
    0.22
    Activations Density 0.037%

    No Known Activations