© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 92982
    Prev
    Next
    INDEX
    Explanations

    CreateObject("Wscript.Shell")

    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_11_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
     informations
    0.34
    φό
    0.34
    symfony
    0.33
    ')+
    0.31
     \
    0.31
    fone
    0.30
    phans
    0.30
     अगर
    0.30
     anhyd
    0.30
     repose
    0.30
    POSITIVE LOGITS
     Diabetic
    0.30
    undering
    0.29
    чі
    0.29
     Frequency
    0.28
    icitis
    0.27
    频率
    0.27
    ᐊ
    0.27
    oches
    0.26
     Mythology
    0.26
    itesi
    0.26
    Activations Density 0.001%

    No Known Activations