© 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. 164878
    Prev
    Next
    INDEX
    Explanations

    code block 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_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
    Mord
    0.39
    ()")
    0.39
    ospor
    0.38
    🦟
    0.35
    road
    0.34
    odon
    0.34
    lç
    0.33
    improve
    0.33
     zweimal
    0.33
    Ξ
    0.33
    POSITIVE LOGITS
     herunter
    0.43
     gun
    0.41
    +"\
    0.40
     собе
    0.38
     plainly
    0.38
     fray
    0.38
     battle
    0.37
     abajo
    0.37
     ब्रे
    0.36
     نوشته
    0.36
    Activations Density 0.087%

    No Known Activations