© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 218215
    Prev
    Next
    INDEX
    Explanations

    percentage change

    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_31_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
     .$
    0.26
     něco
    0.25
     Something
    0.25
    ジュアル
    0.25
    ellular
    0.24
     প্রকৃত
    0.24
     [$
    0.23
    +$
    0.23
     красно
    0.23
     উঠ
    0.23
    POSITIVE LOGITS
     percentage
    0.44
     Percentage
    0.44
    Percentage
    0.42
     percentuale
    0.42
    Ratio
    0.40
    percentage
    0.39
     비율
    0.39
     ratio
    0.38
     porcentaje
    0.38
     percentages
    0.38
    Activations Density 0.001%

    No Known Activations