© 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. 51218
    Prev
    Next
    INDEX
    Explanations

    charting courses (or maps)

    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
     |_
    0.41
    楹
    0.35
    /_
    0.35
     eléct
    0.35
     Soldier
    0.35
     realizzata
    0.35
     PHOT
    0.35
    憶
    0.35
     elegant
    0.34
    modeling
    0.34
    POSITIVE LOGITS
     charted
    0.57
     charting
    0.53
     charts
    0.51
    Carta
    0.49
    Map
    0.47
     cart
    0.45
     chart
    0.45
    Chart
    0.45
    Cart
    0.45
    Charting
    0.45
    Activations Density 0.001%

    No Known Activations