© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 208078
    Prev
    Next
    INDEX
    Explanations

    core concepts

    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_25_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
     reconnect
    0.43
    ्रांत
    0.42
     `=
    0.39
     arXiv
    0.39
     biased
    0.39
    svet
    0.37
    UInt
    0.37
    Muy
    0.36
     reh
    0.36
    Sara
    0.36
    POSITIVE LOGITS
     রোধ
    0.42
    舗
    0.39
    норийска
    0.38
     నిర్మాత
    0.37
     تغ
    0.36
     नियम
    0.36
     گردش
    0.36
    IOUS
    0.35
     evidente
    0.35
     lutego
    0.35
    Activations Density 0.012%

    No Known Activations