© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 228721
    Prev
    Next
    INDEX
    Explanations

    foundation

    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_6_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
    м
    1.02
    ו
    0.98
    se
    0.93
    де
    0.92
    ด
    0.89
    า
    0.89
    as
    0.84
    م
    0.82
     jual
    0.80
    ess
    0.78
    POSITIVE LOGITS
    _
    0.99
    '=
    0.93
    +{
    0.93
    }^
    0.91
     Aeonium
    0.88
    '`
    0.86
     Ambris
    0.86
    motionProxy
    0.86
    randomIndex
    0.85
     Зу
    0.85
    Activations Density 0.004%

    No Known Activations