© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 214755
    Prev
    Next
    INDEX
    Explanations

    fluctu

    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_47_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
     оре
    0.41
     carve
    0.40
     TFT
    0.38
     menilai
    0.37
    嚜
    0.37
     Napole
    0.36
    WRITE
    0.35
     оці
    0.35
     privaten
    0.35
     PROTE
    0.35
    POSITIVE LOGITS
    abilités
    0.41
    abilidades
    0.40
    äuser
    0.39
    哗
    0.39
    รวม
    0.38
    azoo
    0.37
    pias
    0.37
    лары
    0.36
    량을
    0.36
    ப்புகள்
    0.36
    Activations Density 0.001%

    No Known Activations