© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2490
    Prev
    Next
    INDEX
    Explanations

    convertible cars

    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_39_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
    𒋫
    0.45
    鳟
    0.41
     쌓
    0.37
    oursquare
    0.37
     Dixon
    0.37
     μεγαλ
    0.37
     בנו
    0.36
     Bact
    0.36
    rization
    0.36
     হইয়৷
    0.36
    POSITIVE LOGITS
     convertible
    0.96
     convert
    0.84
    convert
    0.84
    Convert
    0.80
     Convertible
    0.80
     Convert
    0.70
     converting
    0.70
     conversion
    0.67
     converted
    0.64
     conversions
    0.63
    Activations Density 0.034%

    No Known Activations