© 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. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 197458
    Prev
    Next
    INDEX
    Explanations

    6

    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_26_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
    Tests
    0.42
    厓
    0.40
    ັນ
    0.39
    Inline
    0.39
    Made
    0.39
    Locator
    0.39
    Units
    0.38
    었는데
    0.38
    тэй
    0.38
    凤
    0.38
    POSITIVE LOGITS
     sum
    0.42
     pane
    0.40
     wartime
    0.40
     lent
    0.39
     carnival
    0.38
     multiplying
    0.38
     calculation
    0.38
     whoever
    0.38
     red
    0.37
     cardamom
    0.37
    Activations Density 0.008%

    No Known Activations