© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 150660
    Prev
    Next
    INDEX
    Explanations

    pal

    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_59_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
    LEV
    0.38
     امید
    0.37
    <0x9D>
    0.36
    ЕМ
    0.36
    呼吸
    0.36
    DUCED
    0.35
    ly
    0.35
    ITE
    0.35
    DOF
    0.35
     प्ला
    0.34
    POSITIVE LOGITS
     undert
    0.45
     Et
    0.43
    ಶ್ಚ
    0.41
     atribut
    0.38
     Aber
    0.36
     dific
    0.36
    eradish
    0.36
    諄
    0.36
    riele
    0.35
     Ruch
    0.35
    Activations Density 0.000%

    No Known Activations