© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 5709
    Prev
    Next
    INDEX
    Explanations

    bracketed areas to fill in

    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_40_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
    itzerland
    0.41
    SSS
    0.36
    ЗА
    0.35
    ###
    0.35
    茅
    0.35
    ➘
    0.35
     ps
    0.34
    啝
    0.34
    整体
    0.34
    Oliv
    0.34
    POSITIVE LOGITS
     Costs
    0.34
     சாத
    0.33
     GDR
    0.33
    getic
    0.33
    hman
    0.32
     Pending
    0.32
    চল
    0.32
    prison
    0.32
     MPR
    0.32
    CURRENT
    0.32
    Activations Density 0.002%

    No Known Activations