© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 109251
    Prev
    Next
    INDEX
    Explanations

    bluesy music or lyrics

    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
    ле
    1.30
    ли
    1.11
    í
    1.00
    леп
    0.92
    ί
    0.89
    ко
    0.87
    是有
    0.84
    ми
    0.84
    ною
    0.84
    之間
    0.83
    POSITIVE LOGITS
    H
    1.64
    A
    1.59
    '
    1.59
    M
    1.52
    ک
    1.48
    U
    1.38
    は
    1.38
    این
    1.36
    AR
    1.35
    T
    1.34
    Activations Density 0.001%

    No Known Activations