© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 133235
    Prev
    Next
    INDEX
    Explanations

    AttributeError

    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_6_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
    ت
    1.95
    т
    1.45
    ل
    1.45
    ق
    1.34
    ?
    1.30
    ک
    1.26
    ק
    1.22
    त
    1.17
    it
    1.16
    .
    1.14
    POSITIVE LOGITS
     في
    0.95
     vět
    0.86
    ın
    0.85
    ında
    0.84
     كل
    0.83
     يت
    0.81
     thiab
    0.80
     natthi
    0.79
    <unused2164>
    0.79
     Τ
    0.79
    Activations Density 0.004%

    No Known Activations