© 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
    2. Gemma-3-27B-IT
    3. 59-GEMMASCOPE-2-TRANSCODER-262K
    4. 148892
    Prev
    Next
    INDEX
    Explanations

    solitude

    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_59_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
     ח
    0.40
    an
    0.38
    सीएस
    0.38
    anan
    0.37
    tsó
    0.37
    とお
    0.37
    笠
    0.37
    onymous
    0.36
    ص
    0.36
    cS
    0.36
    POSITIVE LOGITS
     lists
    0.42
    lagt
    0.40
     ARN
    0.40
     serious
    0.40
     masts
    0.40
     AQU
    0.39
    lace
    0.38
     chem
    0.37
     aces
    0.37
     drips
    0.37
    Activations Density 0.000%

    No Known Activations