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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161055
    Prev
    Next
    INDEX
    Explanations

    describing something admirable

    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
    t
    1.66
     for
    1.43
    r
    1.42
    ল
    1.32
    ט
    1.31
    ু
    1.28
    ן
    1.27
    m
    1.26
    re
    1.24
    ר
    1.23
    POSITIVE LOGITS
    ك
    1.28
    O
    1.25
    bies
    1.20
    ‌ی
    1.20
    我
    1.19
    .
    1.17
    ए
    1.16
     νέα
    1.15
    به
    1.12
    Untuk
    1.11
    Activations Density 0.000%

    No Known Activations