© 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. 219821
    Prev
    Next
    INDEX
    Explanations

    to be followed by

    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
     maggiori
    0.44
     cercando
    0.40
    早く
    0.39
    がありますが
    0.38
    があり
    0.37
    Փ
    0.37
    రావు
    0.37
     जलाने
    0.37
     ಹೋಗ
    0.36
     schreiben
    0.36
    POSITIVE LOGITS
    টক
    0.42
     *-
    0.40
     possibilité
    0.38
     wafer
    0.37
     autoimmune
    0.36
     abon
    0.36
     routes
    0.36
     نړۍ
    0.36
    ++++++++
    0.35
    poss
    0.35
    Activations Density 0.000%

    No Known Activations