© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 109311
    Prev
    Next
    INDEX
    Explanations

    describing changes or modifications

    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_2_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
    ่า
    1.39
    op
    1.08
    ק
    0.98
    ков
    0.98
     което
    0.91
    д
    0.91
    ikt
    0.86
     সময়
    0.86
    кин
    0.84
    くて
    0.84
    POSITIVE LOGITS
    ли
    1.66
     by
    1.61
    is
    1.60
    y
    1.54
    리
    1.43
    e
    1.38
    anın
    1.37
    কে
    1.32
     I
    1.30
    n
    1.28
    Activations Density 0.010%

    No Known Activations