© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 122490
    Prev
    Next
    INDEX
    Explanations

    Bobby names and body structure

    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
    ä
    0.96
    0.70
    ना
    0.65
    ו
    0.64
    ہ
    0.62
    it
    0.62
    त्
    0.61
    ta
    0.58
    pt
    0.57
    to
    0.57
    POSITIVE LOGITS
    ’
    0.73
     vele
    0.66
    ىن
    0.64
     financi
    0.62
    átor
    0.61
     inglese
    0.61
     inay
    0.61
    ؤں
    0.61
     uitgebre
    0.60
    klı
    0.59
    Activations Density 0.000%

    No Known Activations