© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 100067
    Prev
    Next
    INDEX
    Explanations

    urls related to vicuna

    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_14_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
     incipient
    0.48
     ecc
    0.47
    mouseenter
    0.46
     ہتھی
    0.46
     estrogens
    0.46
     indispens
    0.46
     ءَ
    0.45
     NSMutable
    0.45
     chén
    0.45
    mousemove
    0.43
    POSITIVE LOGITS
     Target
    0.54
     Tant
    0.50
     a
    0.50
    oor
    0.49
    नई
    0.48
    जलवायु
    0.48
    气候
    0.46
     climate
    0.46
     Tad
    0.43
    ope
    0.42
    Activations Density 0.000%

    No Known Activations