© 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. 109190
    Prev
    Next
    INDEX
    Explanations

    Iranian, Gav, limoo

    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
    т
    1.80
    ل
    1.55
    t
    1.52
    ي
    1.48
    د
    1.48
    to
    1.41
    l
    1.36
    م
    1.32
    ت
    1.27
    д
    1.27
    POSITIVE LOGITS
    ;
    1.55
    :
    1.21
     a
    1.09
    :}
    1.07
    ian
    1.05
    ),
    0.98
    .}
    0.91
     baits
    0.91
    5
    0.91
     ولوبی
    0.89
    Activations Density 0.000%

    No Known Activations