© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 199883
    Prev
    Next
    INDEX
    Explanations

    philosophers

    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_50_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
     fog
    0.50
    fog
    0.46
    U
    0.45
     U
    0.45
     الع
    0.45
     cloud
    0.43
     Fog
    0.43
    iklet
    0.42
     У
    0.41
     clouds
    0.41
    POSITIVE LOGITS
    Te
    0.42
     Te
    0.40
    derr
    0.38
     рођено
    0.38
    Brewer
    0.37
     তে
    0.37
     وجه
    0.37
    ではありません
    0.36
     Mann
    0.36
    pSensor
    0.36
    Activations Density 0.001%

    No Known Activations