© 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. 84235
    Prev
    Next
    INDEX
    Explanations

    percentage

    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
     Thro
    0.38
     impossibile
    0.38
    डाउन
    0.37
    ▟
    0.37
     physiologique
    0.36
    <0xA0>
    0.36
    だけ
    0.36
     péd
    0.35
    ∥
    0.35
    isinde
    0.35
    POSITIVE LOGITS
    tris
    0.39
    zenia
    0.39
     racemic
    0.39
     princes
    0.38
     lure
    0.38
     raccoon
    0.38
    KQ
    0.38
     Hatter
    0.37
    З
    0.37
     सूट
    0.36
    Activations Density 0.002%

    No Known Activations