© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12505
    Prev
    Next
    INDEX
    Explanations

    popped, broken, adjust, open, sores

    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_13_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
    "।
    0.30
    “.
    0.29
    falt
    0.28
     Universität
    0.28
    imą
    0.27
     Ō
    0.27
     المدينة
    0.27
    বিস্তারিত
    0.26
     buku
    0.26
    వారు
    0.26
    POSITIVE LOGITS
    콥
    0.31
     겁
    0.28
     cohom
    0.27
     enzym
    0.27
     toujours
    0.27
    න්
    0.26
     vertebr
    0.26
     rameaux
    0.26
     prochains
    0.26
     vertebra
    0.26
    Activations Density 0.040%

    No Known Activations