© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45904
    Prev
    Next
    INDEX
    Explanations

    Númenor men

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_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
    b
    0.86
    viving
    0.67
    le
    0.61
    ت
    0.61
    rés
    0.60
    are
    0.57
    r
    0.57
    t
    0.56
    ال
    0.54
    ky
    0.53
    POSITIVE LOGITS
    +")
    0.57
    IZATION
    0.53
    "})
    0.52
     عمليه
    0.52
     +"
    0.52
    ❞
    0.52
    )"
    0.51
    лот
    0.51
     odor
    0.50
     Objekt
    0.50
    Activations Density 0.000%

    No Known Activations