© 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. 84269
    Prev
    Next
    INDEX
    Explanations

    well-

    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
    I
    1.45
    는
    1.45
    Е
    1.36
    के
    1.33
    도
    1.30
    F
    1.23
    は
    1.20
    С
    1.20
    و
    1.18
    Appendix
    1.16
    POSITIVE LOGITS
    า
    1.88
    ле
    1.70
    daki
    1.56
    were
    1.46
    d
    1.45
    та
    1.40
    ler
    1.36
    dq
    1.36
     were
    1.31
    ha
    1.30
    Activations Density 0.000%

    No Known Activations