© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 200973
    Prev
    Next
    INDEX
    Explanations

    stop or close

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     abierto
    0.42
    펼
    0.40
     abiertas
    0.39
    OpenCamera
    0.39
    zadeh
    0.38
     openness
    0.38
    idam
    0.38
     ouverte
    0.37
    ohr
    0.37
     Dac
    0.37
    POSITIVE LOGITS
     Stopped
    0.43
    ۟
    0.38
     Animal
    0.37
    stop
    0.37
    ×
    0.36
    stopped
    0.36
    พ์
    0.36
     Casi
    0.36
     stops
    0.35
    เพียง
    0.35
    Activations Density 0.001%

    No Known Activations