© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2850
    Prev
    Next
    INDEX
    Explanations

    official designation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
    ]=(
    0.40
    )=(
    0.39
    }=(
    0.37
    мес
    0.37
    ఘ
    0.34
    =(
    0.34
     fadeInLeft
    0.33
     Руси
    0.33
     Abbas
    0.32
    ibraries
    0.32
    POSITIVE LOGITS
     ceremony
    0.63
     Ceremony
    0.62
     cerim
    0.58
     مراسم
    0.50
     ceremonies
    0.50
     ceremonia
    0.49
     cérémonie
    0.47
     цере
    0.42
     flagpole
    0.42
    池
    0.39
    Activations Density 0.061%

    No Known Activations