© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199230
    Prev
    Next
    INDEX
    Explanations

    definitely recommend or would

    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_12_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
    uks
    0.58
    adaşlar
    0.53
    laştır
    0.53
    лізу
    0.52
     mounts
    0.52
    mqtt
    0.52
    uzioni
    0.52
    𝓙
    0.52
    ن
    0.51
     australia
    0.50
    POSITIVE LOGITS
     an
    0.57
    ો
    0.52
    an
    0.52
    Evaluating
    0.50
     व्ही
    0.49
    Evaluation
    0.48
    Retention
    0.47
    Payment
    0.47
    шие
    0.47
    ш
    0.47
    Activations Density 0.001%

    No Known Activations