© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 30822
    Prev
    Next
    INDEX
    Explanations

    ascii art elements

    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
    artan
    0.39
    lim
    0.37
    ብ
    0.37
    obs
    0.36
     voy
    0.36
     Оба
    0.36
    óp
    0.36
    Cer
    0.35
    Dz
    0.35
     hyd
    0.35
    POSITIVE LOGITS
    atação
    0.39
    淍
    0.38
    侕
    0.38
     underwhelming
    0.37
     capitol
    0.37
    ...."
    0.37
     Capacitor
    0.37
    jgl
    0.37
    Capitol
    0.37
     GGA
    0.37
    Activations Density 0.004%

    No Known Activations