© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144811
    Prev
    Next
    INDEX
    Explanations

    exclude phrases and conditions

    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_0_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
     are
    1.95
     as
    1.69
    س
    1.63
    ت
    1.36
    to
    1.33
    are
    1.27
    nings
    1.27
    erv
    1.21
    ess
    1.20
    ka
    1.16
    POSITIVE LOGITS
    ை
    1.87
    ва
    1.80
    я
    1.72
    い
    1.71
    ী
    1.70
    ние
    1.55
    ة
    1.52
    يره
    1.50
    на
    1.43
    ம்
    1.40
    Activations Density 0.000%

    No Known Activations