© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89011
    Prev
    Next
    INDEX
    Explanations

    whimpering

    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_3_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
    '
    1.11
    ية
    1.02
    ו
    0.77
    ا
    0.75
    اء
    0.74
    ur
    0.74
    اك
    0.72
    च्या
    0.70
    ді
    0.70
    кри
    0.70
    POSITIVE LOGITS
    and
    0.93
    I
    0.90
    ON
    0.89
    IN
    0.86
    UN
    0.82
    A
    0.79
    H
    0.77
    Aplic
    0.77
    OS
    0.77
    reached
    0.77
    Activations Density 0.001%

    No Known Activations