© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31696
    Prev
    Next
    INDEX
    Explanations

    nonsensical strings

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    translate
    0.41
    Beck
    0.38
    aży
    0.38
    shape
    0.37
     बीज
    0.37
    Mant
    0.37
     Hare
    0.37
    卫
    0.37
     shape
    0.37
    ese
    0.36
    POSITIVE LOGITS
    OPLE
    0.40
    ivity
    0.40
    vall
    0.39
     кай
    0.38
    蛰
    0.38
    ople
    0.38
    chloride
    0.38
     chcia
    0.37
    igram
    0.37
     الجنس
    0.37
    Activations Density 0.001%

    No Known Activations