© 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. 214181
    Prev
    Next
    INDEX
    Explanations

    Hermione

    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
    崁
    0.45
     MAM
    0.43
     veil
    0.42
     Marissa
    0.42
    ∝
    0.41
    dio
    0.41
     Euse
    0.39
    indoor
    0.39
     indoor
    0.38
    環
    0.38
    POSITIVE LOGITS
    बार
    0.45
    Den
    0.42
    Бар
    0.40
    bark
    0.39
    Wt
    0.39
     Den
    0.39
     бар
    0.39
    bourg
    0.39
     Bona
    0.38
    Rq
    0.38
    Activations Density 0.001%

    No Known Activations