© 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
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43635
    Prev
    Next
    INDEX
    Explanations

    IDR, Idris Elba, CIDR block

    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_3_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
    ли
    0.96
    r
    0.83
    ியின்
    0.79
    ない
    0.79
    тся
    0.75
    اب
    0.73
    directed
    0.71
    δια
    0.71
    σι
    0.70
    を手
    0.70
    POSITIVE LOGITS
    ED
    0.90
     for
    0.79
    ET
    0.77
     origami
    0.77
     shorten
    0.75
     numeral
    0.75
    ;
    0.74
     zenith
    0.71
     and
    0.71
                    
    0.70
    Activations Density 0.001%

    No Known Activations