© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 101257
    Prev
    Next
    INDEX
    Explanations

    well

    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_16_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
    Protocol
    0.50
    ä
    0.50
    Group
    0.49
    Pair
    0.49
    x
    0.49
    Cycle
    0.48
    Merged
    0.47
    Adj
    0.46
    Enhanced
    0.46
    CLUSTERED
    0.46
    POSITIVE LOGITS
     partake
    0.54
     prést
    0.52
     hurry
    0.52
     suerte
    0.52
     gym
    0.50
     march
    0.49
     lorry
    0.49
     scrumptious
    0.49
     Celtics
    0.48
    巉
    0.48
    Activations Density 0.000%

    No Known Activations