© 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
    2. Gemma-3-27B-IT
    3. 55-GEMMASCOPE-2-TRANSCODER-262K
    4. 49137
    Prev
    Next
    INDEX
    Explanations

    digits

    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_55_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
     heiß
    0.43
     hot
    0.42
    热
    0.42
     热
    0.42
     வெப்ப
    0.41
     CREAM
    0.40
     hangat
    0.40
    
    0.40
    ourier
    0.39
    熱
    0.38
    POSITIVE LOGITS
    slu
    0.39
    Elon
    0.39
    }_{
    0.38
    Located
    0.37
    Soy
    0.37
    լ
    0.37
    pox
    0.35
    らす
    0.35
    द्दल
    0.35
    Date
    0.34
    Activations Density 0.003%

    No Known Activations