© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26399
    Prev
    Next
    INDEX
    Explanations

    direct

    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_10_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
    _
    0.80
    يت
    0.74
    :
    0.71
    -
    0.71
    ich
    0.71
    .
    0.67
    он
    0.67
     einsch
    0.65
    ile
    0.64
    র
    0.64
    POSITIVE LOGITS
     Direct
    1.14
     direct
    1.13
    direct
    1.11
     directe
    1.05
     diretta
    1.02
    Direct
    0.98
     مستقیم
    0.90
    DIRECT
    0.88
     डायरेक्ट
    0.87
     langsung
    0.86
    Activations Density 0.067%

    No Known Activations