© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 162455
    Prev
    Next
    INDEX
    Explanations

    words ending in ed

    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_2_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
    ال
    1.77
    ون
    1.76
    л
    1.66
    it
    1.58
    لم
    1.55
    يه
    1.46
    ل
    1.41
    can
    1.38
    اء
    1.38
    ار
    1.37
    POSITIVE LOGITS
    :
    1.38
    )
    1.35
    ;
    1.25
    <0x80>
    1.17
    '
    1.13
     revital
    1.00
    ↵
    1.00
    ),
    1.00
     המת
    0.99
     prerogative
    0.99
    Activations Density 0.000%

    No Known Activations