© 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. 233077
    Prev
    Next
    INDEX
    Explanations

    Lee

    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
    ViewModel
    0.48
    mort
    0.44
    John
    0.43
     B
    0.42
    Victoria
    0.41
     Gone
    0.40
    Mort
    0.40
    wine
    0.39
    djang
    0.39
     Morton
    0.38
    POSITIVE LOGITS
     LEE
    0.52
    LEE
    0.47
     lees
    0.47
     lee
    0.45
     Ang
    0.45
     Lee
    0.43
     Lees
    0.39
    kend
    0.39
    李
    0.39
    詡
    0.38
    Activations Density 0.028%

    No Known Activations