© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 163010
    Prev
    Next
    INDEX
    Explanations

    Progestin | Assembly

    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_31_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
    letters
    0.37
    Letter
    0.33
     lettres
    0.33
    forschung
    0.33
    ổng
    0.33
    皺
    0.33
     Letter
    0.32
    orschung
    0.32
    Ful
    0.31
    素晴らしい
    0.31
    POSITIVE LOGITS
     Loop
    0.38
    )=>
    0.36
     Loops
    0.34
     loop
    0.34
    तीय
    0.33
     Remix
    0.33
    ೈಸ
    0.33
     इज
    0.33
    cevam
    0.33
     favourite
    0.32
    Activations Density 0.000%

    No Known Activations