© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40767
    Prev
    Next
    INDEX
    Explanations

    EST timestamps

    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_11_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
    ă
    0.52
     질
    0.50
    ā
    0.50
     según
    0.49
     kā
    0.48
    aciju
    0.48
    isasi
    0.48
     negated
    0.47
    oría
    0.47
     IDA
    0.47
    POSITIVE LOGITS
    ，
    0.52
    दायक
    0.52
    })$,
    0.50
    音乐
    0.50
    题
    0.50
    》，
    0.50
    电脑
    0.50
    ד
    0.49
    Benzoimidazol
    0.49
    كامل
    0.48
    Activations Density 0.001%

    No Known Activations