© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4513
    Prev
    Next
    INDEX
    Explanations

    structured data delimiters

    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_39_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
     alvo
    0.45
    走
    0.41
     달려
    0.39
    Melissa
    0.38
    מל
    0.38
    meld
    0.37
     mél
    0.37
    Charg
    0.37
     Melan
    0.37
     Annu
    0.36
    POSITIVE LOGITS
    icorn
    0.45
    ornis
    0.39
     emotional
    0.37
    gable
    0.37
    観
    0.36
    KeyEvent
    0.36
     кош
    0.36
     આમ
    0.36
     adjustment
    0.35
    ardo
    0.35
    Activations Density 0.040%

    No Known Activations