© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 60786
    Prev
    Next
    INDEX
    Explanations

    Atorvastatin; netorare; Coffee

    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_2_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
    یت
    1.55
    ને
    1.28
    ی
    1.28
    یان
    1.26
    ної
    1.16
    at
    1.15
    ில்
    1.15
    이었
    1.13
    ת
    1.12
    тэй
    1.11
    POSITIVE LOGITS
     a
    1.35
    。
    1.35
    de
    1.09
    la
    1.01
    ),
    1.00
    ü
    0.99
    re
    0.98
    )
    0.97
    b
    0.96
    K
    0.96
    Activations Density 0.000%

    No Known Activations