© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78843
    Prev
    Next
    INDEX
    Explanations

    resignation Letter

    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_0_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
    자
    1.57
    a
    1.54
    m
    1.50
    টা
    1.36
    Przeczytaj
    1.33
    ский
    1.27
    o
    1.27
    1.23
    вает
    1.20
    of
    1.17
    POSITIVE LOGITS
    asing
    1.30
    的目标
    1.29
    的声音
    1.20
     legitim
    1.20
    us
    1.19
    та
    1.19
     synthes
    1.17
    ↵
    1.15
    ick
    1.13
    ang
    1.10
    Activations Density 0.000%

    No Known Activations