© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 176156
    Prev
    Next
    INDEX
    Explanations

    animals executing

    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_20_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
     actriz
    0.48
    ټبال
    0.46
     respetar
    0.46
    鍱
    0.46
     equipo
    0.45
     сохранить
    0.45
     हिस्सा
    0.45
     öyle
    0.44
     いう
    0.44
     campanha
    0.44
    POSITIVE LOGITS
    Chapter
    0.45
     realms
    0.45
     premiers
    0.43
     spaces
    0.41
     mignon
    0.40
    ruary
    0.40
    ／
    0.39
    🟦
    0.39
     environments
    0.39
     знания
    0.39
    Activations Density 0.000%

    No Known Activations