© 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. 213940
    Prev
    Next
    INDEX
    Explanations

    company names

    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
    śle
    0.42
    簫
    0.39
    술
    0.39
     gau
    0.38
    сында
    0.38
     Vgl
    0.38
     Cly
    0.37
    LETED
    0.37
    Cue
    0.36
     আনন্দ
    0.36
    POSITIVE LOGITS
    ichi
    0.42
     הנ
    0.42
    ഹ
    0.41
     H
    0.41
    ich
    0.39
     Н
    0.39
     muss
    0.39
    根
    0.38
     নাহি
    0.37
    NQ
    0.37
    Activations Density 0.004%

    No Known Activations