© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 99087
    Prev
    Next
    INDEX
    Explanations

    things to break

    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_16_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
    كى
    0.54
    كي
    0.52
     まあ
    0.50
     publier
    0.49
     Decreto
    0.48
    ни
    0.47
    ut
    0.47
    懟
    0.46
    肱
    0.46
     verbinden
    0.46
    POSITIVE LOGITS
    enst
    0.51
    アクセ
    0.48
    accessible
    0.47
    command
    0.46
    istor
    0.45
     அப்போது
    0.44
     command
    0.43
    Haw
    0.42
     paramilitary
    0.42
    conce
    0.42
    Activations Density 0.000%

    No Known Activations