© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 213055
    Prev
    Next
    INDEX
    Explanations

    lab, ash, za

    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_5_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
    ש
    1.41
    يمكن
    1.30
    ત
    1.16
    ד
    1.14
     \
    1.13
    ال
    1.13
    ה
    1.09
     お
    1.09
    ING
    1.05
     ג
    1.05
    POSITIVE LOGITS
    ’
    1.37
    ure
    1.18
    iken
    1.16
    ils
    1.13
    ressed
    1.09
    ны
    1.07
    iter
    1.07
    مان
    1.05
    ron
    1.01
    rou
    1.00
    Activations Density 0.000%

    No Known Activations