© 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. 196976
    Prev
    Next
    INDEX
    Explanations

    approximations

    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
     px
    0.42
    sony
    0.42
    쇤
    0.41
     ox
    0.39
    ancellation
    0.39
     Συν
    0.38
     oxford
    0.38
     lactis
    0.38
     ऑक्स
    0.37
    rection
    0.37
    POSITIVE LOGITS
    Trap
    0.40
     Trap
    0.39
    úly
    0.38
    gesellschaft
    0.36
    ricult
    0.36
     つい
    0.36
    рь
    0.35
    ห์
    0.35
    楤
    0.35
     Pump
    0.35
    Activations Density 0.001%

    No Known Activations