© 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. 35335
    Prev
    Next
    INDEX
    Explanations

    react and ui hooks

    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
    宣言
    0.36
    achricht
    0.36
     Aura
    0.35
     aura
    0.34
    žel
    0.34
     uni
    0.34
     usuario
    0.33
    芠
    0.33
    রাশ
    0.33
     generations
    0.32
    POSITIVE LOGITS
     PTE
    0.39
    교
    0.39
     cabo
    0.38
     деревя
    0.38
     конце
    0.37
     Bain
    0.36
     叶
    0.36
     Pape
    0.35
     interpolate
    0.34
     CIE
    0.34
    Activations Density 0.000%

    No Known Activations