© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 91033
    Prev
    Next
    INDEX
    Explanations

    information/data

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
     was
    0.47
     (\$
    0.45
     (<
    0.44
     may
    0.43
     hasn
    0.43
     determined
    0.42
     (§
    0.42
     (
    0.41
    这么
    0.41
     （
    0.40
    POSITIVE LOGITS
     Pays
    0.63
     Builds
    0.50
     Ended
    0.49
     Opens
    0.48
     Finds
    0.48
     Calls
    0.47
     Adds
    0.46
     Would
    0.44
     Writes
    0.44
     Considering
    0.43
    Activations Density 0.004%

    No Known Activations