© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35983
    Prev
    Next
    INDEX
    Explanations

    mildew, mold, steel, Paddington

    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_3_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
    dings
    0.76
    dell
    0.73
     فِي
    0.73
    б
    0.73
    emen
    0.72
    ي
    0.72
    detected
    0.69
    𝓭
    0.69
     ingrédients
    0.68
    𝚍
    0.68
    POSITIVE LOGITS
    us
    1.00
    ה
    0.91
     of
    0.80
    作り
    0.79
    ри
    0.77
    ]
    0.77
    um
    0.73
     It
    0.73
    (
    0.71
    ه
    0.70
    Activations Density 0.006%

    No Known Activations