© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44902
    Prev
    Next
    INDEX
    Explanations

    backing tracks or integration

    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_3_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
    та
    0.66
    <0xAB>
    0.65
    zoomSeekBar
    0.64
    नंतर
    0.62
     singularities
    0.62
     quyết
    0.60
    iem
    0.59
     insertions
    0.58
     solos
    0.58
    <0xBF>
    0.57
    POSITIVE LOGITS
     is
    0.89
    t
    0.87
     .
    0.80
    ad
    0.75
    ために
    0.73
    人
    0.72
    d
    0.70
    es
    0.64
    .
    0.64
    PS
    0.63
    Activations Density 0.002%

    No Known Activations