© 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
    2. Gemma-3-27B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 260976
    Prev
    Next
    INDEX
    Explanations

    raging

    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
    ي
    1.52
    자
    1.33
    i
    1.30
    ้
    1.29
    。
    1.28
    י
    1.25
    ות
    1.23
    ли
    1.20
     desenvolv
    1.17
    ور
    1.16
    POSITIVE LOGITS
    of
    1.40
    ave
    1.24
    and
    1.18
    ank
    1.00
    clothing
    1.00
    avin
    0.98
    eno
    0.96
    ian
    0.96
    bath
    0.95
    potential
    0.95
    Activations Density 0.000%

    No Known Activations