© 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. 35845
    Prev
    Next
    INDEX
    Explanations

    microsoft corporation websites

    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
    consistency
    0.41
    esség
    0.34
    dimensionality
    0.34
     മേ
    0.33
     عند
    0.32
     മാറി
    0.32
    ფერ
    0.32
    己
    0.32
    AllWindows
    0.32
    ird
    0.31
    POSITIVE LOGITS
     empowers
    0.40
     કા
    0.39
     encourages
    0.38
     prefers
    0.38
     MSA
    0.37
    iza
    0.37
     mobil
    0.37
     MS
    0.36
    ್ರಾ
    0.36
     farm
    0.34
    Activations Density 0.031%

    No Known Activations