© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 204119
    Prev
    Next
    INDEX
    Explanations

    suffix 'ión' or 'ion'

    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_6_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
    ä
    1.20
    )."
    0.96
    }.
    0.93
     <
    0.91
    em
    0.89
    de
    0.87
     =
    0.87
     -
    0.86
    ien
    0.84
    é
    0.84
    POSITIVE LOGITS
    H
    0.97
    ון
    0.91
    ת
    0.89
    ל
    0.89
    ppure
    0.85
    ו
    0.84
    '
    0.83
    לים
    0.82
    P
    0.82
    Ц
    0.82
    Activations Density 0.000%

    No Known Activations