© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 138282
    Prev
    Next
    INDEX
    Explanations

    early American history

    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
    KeyboardMarkup
    0.46
     Dee
    0.42
     థ
    0.39
    dilate
    0.38
     incur
    0.38
    ))+\
    0.38
     cranial
    0.38
    Rogers
    0.38
    Dee
    0.37
     Бого
    0.37
    POSITIVE LOGITS
    ToIndex
    0.40
    Ⅷ
    0.40
    infty
    0.38
     seller
    0.38
     perennials
    0.37
     Seller
    0.37
    atosis
    0.37
     cd
    0.36
    ánea
    0.36
     sc
    0.36
    Activations Density 0.008%

    No Known Activations