© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 210781
    Prev
    Next
    INDEX
    Explanations

    fi followed by words starting with 'g', 'w', 'endish', 'ords', 'est', 'ends', 'ery', 'ord'

    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_5_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
    c
    1.68
    t
    1.56
    e
    1.55
    a
    1.39
    b
    1.34
    i
    1.32
    ৩
    1.30
    י
    1.29
    at
    1.27
    v
    1.27
    POSITIVE LOGITS
     in
    1.48
    ators
    1.05
     (
    0.99
    НО
    0.94
    ässer
    0.92
    с
    0.92
    <0xA8>
    0.92
    itation
    0.91
    在
    0.91
    ీ
    0.91
    Activations Density 0.000%

    No Known Activations