© 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. 156148
    Prev
    Next
    INDEX
    Explanations

    poems

    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
     Harold
    0.37
    Harold
    0.37
    藕
    0.37
     пли
    0.36
     discriminated
    0.34
    ott
    0.34
    ceptible
    0.34
    Datas
    0.34
    referenced
    0.34
    TURN
    0.33
    POSITIVE LOGITS
     Foster
    0.42
    ysing
    0.38
    /'.$
    0.37
     Triumph
    0.37
     allons
    0.37
     voices
    0.36
    Thing
    0.36
    ில்
    0.36
     Фо
    0.36
     ㅛ
    0.36
    Activations Density 0.001%

    No Known Activations