© 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. 219974
    Prev
    Next
    INDEX
    Explanations

    logo, nav, a, li

    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
    navbarNav
    0.42
    설
    0.37
    견
    0.37
     gird
    0.37
    ග
    0.35
    항
    0.35
     ઓ
    0.35
     ngũ
    0.35
    벌
    0.35
    ታት
    0.34
    POSITIVE LOGITS
    一声
    0.39
     Despite
    0.38
     tattoos
    0.37
     sonidos
    0.36
     derives
    0.35
     atypical
    0.35
     tones
    0.35
     flowing
    0.35
     profitable
    0.35
     orifices
    0.35
    Activations Density 0.002%

    No Known Activations