© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 209719
    Prev
    Next
    INDEX
    Explanations

    audio, audios, audio, pulseaudio

    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
    জ
    1.12
    d
    1.00
    ת
    0.94
    at
    0.93
    ज
    0.90
    ش
    0.87
    :
    0.87
    م
    0.87
    د
    0.85
    ა
    0.84
    POSITIVE LOGITS
    0.98
     (
    0.95
    9
    0.93
    ৬
    0.85
    6
    0.82
    ৯
    0.78
    0
    0.73
     ulic
    0.68
     ऑन
    0.65
     ontology
    0.65
    Activations Density 0.000%

    No Known Activations