© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 141962
    Prev
    Next
    INDEX
    Explanations

    infinity

    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_0_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
    brushes
    1.15
    də
    1.13
    ců
    1.10
    dí
    1.09
    ”
    1.07
    Pokud
    1.05
    ی
    1.05
    "
    1.03
    东西
    1.02
    ům
    1.02
    POSITIVE LOGITS
    ль
    1.71
    ת
    1.58
    い
    1.49
    ล
    1.37
    ن
    1.34
    ある
    1.31
    ל
    1.30
    ic
    1.29
    ین
    1.29
    บ
    1.29
    Activations Density 0.000%

    No Known Activations