© 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. 196071
    Prev
    Next
    INDEX
    Explanations

    Tech and 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
    egaard
    0.45
    ତ୍
    0.40
     റേ
    0.39
     Odin
    0.39
    ্কা
    0.38
     Mobility
    0.37
    ্যাটে
    0.37
    伽
    0.37
    优雅
    0.37
    Gaming
    0.37
    POSITIVE LOGITS
    বাল
    0.42
    бол
    0.39
    BOT
    0.37
     harassing
    0.37
    THREAD
    0.37
     Lact
    0.36
    ¬
    0.36
     Harlan
    0.35
     booty
    0.35
    مكن
    0.35
    Activations Density 0.043%

    No Known Activations