© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 89714
    Prev
    Next
    INDEX
    Explanations

    greeting

    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_23_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
     কিছু
    0.19
    кости
    0.19
     junio
    0.19
     ];
    0.18
    किस्तानी
    0.18
     LO
    0.18
    騏
    0.18
    lemente
    0.18
     Rossa
    0.18
    L
    0.18
    POSITIVE LOGITS
    addColorStop
    0.21
    aanse
    0.21
     შესახებ
    0.21
    èque
    0.21
     ожида
    0.20
    orf
    0.19
    ూర్
    0.19
    эт
    0.19
    ambient
    0.19
    oworld
    0.19
    Activations Density 0.002%

    No Known Activations