© 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. 246433
    Prev
    Next
    INDEX
    Explanations

    Document, const

    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
     halinde
    0.38
    SU
    0.38
     Hale
    0.38
     எங்க
    0.37
    隷
    0.37
     ¹
    0.36
     *$
    0.36
     جوئے
    0.35
     Selection
    0.35
    adjacent
    0.34
    POSITIVE LOGITS
     orientations
    0.44
     Orient
    0.43
     Tener
    0.39
    จิต
    0.39
     شار
    0.38
     pracę
    0.38
     ори
    0.38
     Ziel
    0.38
    웃
    0.38
    Orient
    0.38
    Activations Density 0.000%

    No Known Activations