© 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. 202761
    Prev
    Next
    INDEX
    Explanations

    stream editor

    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
     Monteiro
    0.40
    KeyboardView
    0.39
    patx
    0.39
    streams
    0.39
    濤
    0.38
     Brentford
    0.38
     kebut
    0.37
    ธาร
    0.37
    Brent
    0.36
     Bremer
    0.36
    POSITIVE LOGITS
     Pras
    0.42
     obs
    0.40
    }+
    0.39
     fah
    0.39
     insert
    0.38
    插入
    0.38
     fxaa
    0.38
     callable
    0.37
    vika
    0.37
    |+
    0.37
    Activations Density 0.002%

    No Known Activations