© 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. 206447
    Prev
    Next
    INDEX
    Explanations

    awards season

    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
     solcher
    0.40
    users
    0.40
    /
    0.37
     such
    0.36
    B
    0.36
     във
    0.35
    planetary
    0.35
    ющей
    0.34
    active
    0.34
    relevant
    0.34
    POSITIVE LOGITS
    ឹ
    0.43
     ойнотуу
    0.43
     ойно
    0.43
     ritmo
    0.42
     geranium
    0.42
     erratic
    0.41
    Transicao
    0.41
     sentimento
    0.41
    鋏
    0.41
     mandamus
    0.41
    Activations Density 0.000%

    No Known Activations