© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 232926
    Prev
    Next
    INDEX
    Explanations

    expressing belief

    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
     Hermann
    0.40
     ควร
    0.40
    鎂
    0.39
     podrían
    0.39
    轂
    0.37
     könnte
    0.37
     могло
    0.37
    หา
    0.36
    ußen
    0.35
     މި
    0.35
    POSITIVE LOGITS
     மகி
    0.40
    ipient
    0.39
    ীকার
    0.39
    Cour
    0.39
    agno
    0.38
     upgrade
    0.38
    τούν
    0.38
    embangan
    0.37
    皘
    0.36
    upan
    0.36
    Activations Density 0.002%

    No Known Activations