© 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. 131077
    Prev
    Next
    INDEX
    Explanations

    programming or software

    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
    Wars
    0.43
    ೖ
    0.38
    덫
    0.38
     Bé
    0.37
    खास्त
    0.36
    汪
    0.36
    釗
    0.36
    ดาว
    0.36
    mmol
    0.35
     ego
    0.35
    POSITIVE LOGITS
    かが
    0.42
    ELLE
    0.42
    アラ
    0.42
    Om
    0.40
    ORMAL
    0.40
     Gir
    0.40
    othes
    0.39
     gir
    0.38
    淩
    0.38
    اله
    0.38
    Activations Density 0.008%

    No Known Activations