© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 212001
    Prev
    Next
    INDEX
    Explanations

    poetry

    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_43_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
    ระดับ
    0.42
    级
    0.41
     level
    0.39
    level
    0.39
     metering
    0.38
     measuring
    0.37
    級
    0.37
     Independ
    0.37
     alternately
    0.37
     Niveau
    0.37
    POSITIVE LOGITS
    ンド
    0.40
     Glory
    0.39
    alım
    0.37
    жного
    0.36
    风
    0.36
    izh
    0.36
    fiz
    0.35
     الداخلية
    0.35
    irim
    0.35
     спорттук
    0.34
    Activations Density 0.000%

    No Known Activations