© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 32955
    Prev
    Next
    INDEX
    Explanations

    attached hereto as Exhibit

    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_40_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
     Libby
    0.40
    ember
    0.38
     dru
    0.38
     tin
    0.35
     consolidation
    0.35
    際
    0.35
     Barrington
    0.35
     Steven
    0.35
     beton
    0.35
     druk
    0.35
    POSITIVE LOGITS
    ⌟
    0.40
    assung
    0.39
     ગયો
    0.38
    aderamente
    0.38
    依靠
    0.38
     মর্ম
    0.38
     आया
    0.38
    ogany
    0.37
     fascia
    0.37
     rely
    0.36
    Activations Density 0.001%

    No Known Activations