© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 247894
    Prev
    Next
    INDEX
    Explanations

    sing

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    singer
    0.57
     Singer
    0.52
    Singer
    0.49
     सिंगर
    0.49
     singer
    0.47
    ের
    0.45
    sız
    0.45
    s
    0.44
    song
    0.44
    following
    0.43
    POSITIVE LOGITS
     Along
    0.65
    Along
    0.64
     along
    0.56
    along
    0.55
    oprene
    0.49
     вдоль
    0.47
    沿
    0.46
    Able
    0.42
     lungo
    0.39
     Largo
    0.39
    Activations Density 0.000%

    No Known Activations