© 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. 39708
    Prev
    Next
    INDEX
    Explanations

    referring to

    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
    л
    0.66
    lt
    0.64
    ts
    0.64
    g
    0.64
    t
    0.62
    la
    0.57
     (
    0.57
     headlight
    0.57
     economic
    0.56
    il
    0.55
    POSITIVE LOGITS
     为
    0.70
     هذا
    0.66
    媺
    0.60
     对象
    0.58
     එය
    0.57
    берите
    0.57
    Мар
    0.57
     其
    0.56
     관
    0.55
    Merc
    0.55
    Activations Density 0.002%

    No Known Activations