© 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. 21611
    Prev
    Next
    INDEX
    Explanations

    Nr/number identifier

    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
     Nose
    0.48
    鼻
    0.40
     nose
    0.39
     заво
    0.38
     Clarendon
    0.38
    Ivan
    0.36
    Warren
    0.36
    酲
    0.35
     பெரும்
    0.35
    nose
    0.34
    POSITIVE LOGITS
     nr
    3.14
    nr
    3.08
     NR
    2.77
     Nr
    2.69
    Nr
    2.69
    NR
    2.48
     nb
    1.73
     NRI
    1.65
     Nb
    1.57
    Nb
    1.52
    Activations Density 0.057%

    No Known Activations