© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91201
    Prev
    Next
    INDEX
    Explanations

    glow up

    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_3_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
     synchronous
    0.64
    ¹.
    0.64
     of
    0.63
    O
    0.63
     has
    0.60
     realization
    0.60
    im
    0.59
     представ
    0.59
    ए
    0.59
    여
    0.59
    POSITIVE LOGITS
    坳
    0.73
    NOW
    0.64
    Server
    0.63
    Gauge
    0.61
    cB
    0.61
    UserName
    0.60
    सभा
    0.59
    Qa
    0.57
    lav
    0.57
    唝
    0.57
    Activations Density 0.002%

    No Known Activations