© 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. 228370
    Prev
    Next
    INDEX
    Explanations

    PWD current directory, password, or determination

    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
    ट
    1.13
    ية
    1.11
    ut
    1.09
    _
    1.07
    6
    1.07
    ৬
    1.06
    ---------------
    1.04
    ।
    1.04
    ৭
    0.97
    \}
    0.97
    POSITIVE LOGITS
    ன்
    0.98
    าม
    0.96
    ين
    0.92
     piazza
    0.92
    ك
    0.90
    મ
    0.89
     kaleidoscope
    0.89
    ியை
    0.88
    ছে
    0.88
    ной
    0.88
    Activations Density 0.000%

    No Known Activations