© 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. 84230
    Prev
    Next
    INDEX
    Explanations

    poet

    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
    s
    2.20
    t
    1.98
    a
    1.96
     that
    1.67
    $.
    1.65
    ről
    1.61
    Р
    1.59
    ties
    1.52
    ti
    1.52
    Т
    1.52
    POSITIVE LOGITS
    وم
    1.23
    ér
    1.20
    äst
    1.19
    ர
    1.18
     côte
    1.13
    ം
    1.12
    ла
    1.11
    ி
    1.10
     básicos
    1.09
    illä
    1.07
    Activations Density 0.000%

    No Known Activations