© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 14-GEMMASCOPE-2-TRANSCODER-262K
    4. 99360
    Prev
    Next
    INDEX
    Explanations

    color, style, sentinel, singleton

    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_14_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
    BDA
    0.60
    ;
    0.57
    :
    0.56
    ast
    0.55
    hour
    0.55
    '
    0.54
    }
    0.54
    ha
    0.53
    דר
    0.53
    Now
    0.52
    POSITIVE LOGITS
     παιδιά
    0.66
     supernovae
    0.60
     ကျွန်
    0.59
     п
    0.58
     crianças
    0.58
     οι
    0.58
     குழந்தைகள்
    0.57
    ेड
    0.56
     Maastricht
    0.55
     Какие
    0.55
    Activations Density 0.000%

    No Known Activations