© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14466
    Prev
    Next
    INDEX
    Explanations

    you want

    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_40_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
     wanna
    0.37
    Want
    0.37
    BSD
    0.34
    ūt
    0.34
    ">:
    0.34
     Want
    0.33
    年月日
    0.33
    vens
    0.32
     verrà
    0.32
    녓
    0.32
    POSITIVE LOGITS
     자신이
    0.39
     которую
    0.38
     Huerta
    0.37
    自分が
    0.37
    드를
    0.37
    ண
    0.36
     தாம்
    0.35
    藏
    0.35
     kterou
    0.35
    단을
    0.35
    Activations Density 0.640%

    No Known Activations