© 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. 110076
    Prev
    Next
    INDEX
    Explanations

    holidays

    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
    b
    1.46
    ون
    1.45
    ية
    1.37
    p
    1.31
    ur
    1.24
    ز
    1.23
    2
    1.21
    um
    1.16
    ies
    1.16
    ’
    1.16
    POSITIVE LOGITS
    い
    1.57
    یش
    1.25
    า
    1.16
    た
    1.15
    取り
    1.14
    دی
    1.13
    ！？
    1.11
    )：
    1.11
    어
    1.11
    یت
    1.09
    Activations Density 0.000%

    No Known Activations