© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 235344
    Prev
    Next
    INDEX
    Explanations

    separator line

    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_46_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
    èn
    0.44
     faculty
    0.43
     facult
    0.42
     '*
    0.41
    <.
    0.37
    _.
    0.36
     basic
    0.35
     ',
    0.35
    __(
    0.35
    '$.
    0.35
    POSITIVE LOGITS
    墺
    0.48
    ocaps
    0.41
    nashville
    0.41
    𒄑
    0.40
     आंसर
    0.40
    日本の
    0.40
     നമ്പർ
    0.40
    Counsel
    0.39
     সর্বনিম্ন
    0.38
     geführt
    0.38
    Activations Density 0.001%

    No Known Activations