© 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. 130911
    Prev
    Next
    INDEX
    Explanations

    conviction consequences

    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
    YER
    0.91
    ESD
    0.89
    EL
    0.83
    CPU
    0.83
    وعه
    0.78
    리어
    0.76
    води
    0.75
    _
    0.75
    وان
    0.75
     wares
    0.75
    POSITIVE LOGITS
    c
    1.30
    v
    1.05
    ti
    1.03
    cs
    1.03
    sch
    1.02
    k
    0.98
    ta
    0.96
    ada
    0.96
    tp
    0.95
    ng
    0.93
    Activations Density 0.000%

    No Known Activations