© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66411
    Prev
    Next
    INDEX
    Explanations

    me too

    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_41_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
     Web
    0.70
    Web
    0.55
     WEB
    0.54
    WEB
    0.48
     वेब
    0.44
    web
    0.44
    ⑵
    0.43
     web
    0.42
     웹
    0.42
    叅
    0.41
    POSITIVE LOGITS
     me
    2.00
     Me
    1.85
    Me
    1.76
    me
    1.49
     ME
    1.27
     ме
    1.25
    ME
    1.01
     मे
    0.96
     meille
    0.95
     mee
    0.95
    Activations Density 0.001%

    No Known Activations