© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 166796
    Prev
    Next
    INDEX
    Explanations

    transport and numbers

    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_56_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
     №
    0.43
     Nº
    0.43
    №
    0.42
     pass
    0.41
     nr
    0.40
     Along
    0.37
     #
    0.37
    铨
    0.37
     nº
    0.37
     sè
    0.36
    POSITIVE LOGITS
     gevonden
    0.45
     banned
    0.39
     hern
    0.38
     disliked
    0.38
    removed
    0.37
     hypotheses
    0.36
    deleted
    0.36
    matched
    0.36
    人材
    0.36
     пра
    0.35
    Activations Density 0.001%

    No Known Activations