© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 216633
    Prev
    Next
    INDEX
    Explanations

    online marketing

    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_50_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
    ERI
    0.41
     Wra
    0.39
     কে
    0.39
     Environmental
    0.39
    ποι
    0.39
     capac
    0.38
     티
    0.38
     pur
    0.38
     تي
    0.37
    ере
    0.37
    POSITIVE LOGITS
     ഹിന്ദ
    0.40
    $\--
    0.39
    ટક
    0.39
     হওয়
    0.38
    鹭
    0.38
    Jwt
    0.37
     forgery
    0.36
    Nw
    0.36
    寂
    0.36
     varsity
    0.35
    Activations Density 0.000%

    No Known Activations