© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 109994
    Prev
    Next
    INDEX
    Explanations

    hearty

    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_2_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
    a
    1.91
    ن
    1.42
    น
    1.42
    ’
    1.38
    '
    1.34
    IM
    1.33
    e
    1.30
    ন
    1.30
    IN
    1.29
    I
    1.20
    POSITIVE LOGITS
    ק
    1.23
    ために
    1.20
    1.18
    ンの
    1.12
    니
    1.03
     moisturizing
    0.95
    세요
    0.93
    во
    0.93
    ጣም
    0.92
    ز
    0.92
    Activations Density 0.000%

    No Known Activations