© 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. 8238
    Prev
    Next
    INDEX
    Explanations

    your project changes

    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
     anticor
    0.38
    อังกฤษ
    0.38
     लॉ
    0.38
    output
    0.37
    Output
    0.37
    nabla
    0.36
    Peach
    0.36
    "/><
    0.36
    盾
    0.36
    蛉
    0.36
    POSITIVE LOGITS
     Indexed
    0.40
     Past
    0.39
     Rider
    0.39
     filled
    0.39
    ങ്ങളിലും
    0.39
     mê
    0.39
    translations
    0.39
     translations
    0.38
     खड़ी
    0.38
    ᐢ
    0.38
    Activations Density 0.002%

    No Known Activations