© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42602
    Prev
    Next
    INDEX
    Explanations

    цепка, ценить, оцепенение

    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
     (
    0.79
     for
    0.77
     compression
    0.74
     நான்கு
    0.73
     toned
    0.72
    ی
    0.70
    یت
    0.70
     cranial
    0.70
     capacitance
    0.69
    да
    0.68
    POSITIVE LOGITS
    l
    0.84
    Acc
    0.75
    ল
    0.74
    ل
    0.71
    লন
    0.71
    ون
    0.70
    im
    0.66
    Accent
    0.66
    För
    0.64
    vorschau
    0.64
    Activations Density 0.007%

    No Known Activations