© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 176694
    Prev
    Next
    INDEX
    Explanations

    sentiment modifiers and evaluative adjectives

    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_20_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    equal
    0.44
    current
    0.44
     juc
    0.42
    inch
    0.41
    eyed
    0.41
    inclusive
    0.39
    M
    0.39
     દિ
    0.39
    Thank
    0.39
     Jal
    0.39
    POSITIVE LOGITS
     pamię
    0.44
     mémoire
    0.43
    ىلى
    0.42
    ryk
    0.42
    ätten
    0.42
     memória
    0.42
    roje
    0.41
    ąg
    0.40
    㫣
    0.40
    RICK
    0.39
    Activations Density 0.016%

    No Known Activations