© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 80683
    Prev
    Next
    INDEX
    Explanations

    specific characters

    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_53_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
     لش
    0.48
    )}_
    0.40
     peter
    0.40
    тература
    0.40
     l
    0.39
    就好了
    0.39
     मिलते
    0.38
    
    0.38
     tent
    0.38
     su
    0.37
    POSITIVE LOGITS
    รร
    0.39
    ǎi
    0.39
     Si
    0.38
    峩
    0.37
     Sih
    0.37
     fingerprints
    0.36
    邈
    0.36
     Thermo
    0.36
    ค้น
    0.35
     Lah
    0.35
    Activations Density 0.000%

    No Known Activations