© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44077
    Prev
    Next
    INDEX
    Explanations

    Zermatt

    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_3_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
    C
    1.02
     It
    0.82
    ς
    0.81
    B
    0.75
    S
    0.72
    T
    0.72
    P
    0.71
    ="
    0.71
    R
    0.70
    Pid
    0.66
    POSITIVE LOGITS
    0
    0.82
    д
    0.80
    𝗶
    0.75
    𝚒
    0.67
    ０
    0.64
    𝚊
    0.64
    ج
    0.63
     tiden
    0.61
    っいて
    0.61
     тър
    0.61
    Activations Density 0.004%

    No Known Activations