© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35809
    Prev
    Next
    INDEX
    Explanations

    Directors' remuneration

    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_31_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
    frequencies
    0.40
    bserv
    0.39
     আল্লাহ
    0.38
     शमी
    0.38
    আল্লাহ
    0.38
     midsole
    0.36
     topmost
    0.35
     돼
    0.35
    ষেধ
    0.35
     CuSO
    0.35
    POSITIVE LOGITS
     Standards
    0.41
     parted
    0.40
     Wants
    0.39
    बे
    0.37
    icoter
    0.37
     vodi
    0.37
    icea
    0.37
     Want
    0.37
     good
    0.36
     टेम्प
    0.36
    Activations Density 0.030%

    No Known Activations