© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 199261
    Prev
    Next
    INDEX
    Explanations

    Gruy and Granny

    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
    awas
    0.42
    𝟖
    0.40
    ुका
    0.40
    uate
    0.39
    ḧ
    0.38
     తెర
    0.38
    oco
    0.38
     recieved
    0.37
    িবে
    0.37
    ≫
    0.37
    POSITIVE LOGITS
    angsa
    0.37
     IANS
    0.35
    korn
    0.35
    𝙔
    0.35
    नीर
    0.34
     jari
    0.34
    沅
    0.34
    svr
    0.34
    Two
    0.33
    ọt
    0.33
    Activations Density 0.001%

    No Known Activations