© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242417
    Prev
    Next
    INDEX
    Explanations

    code in conversation

    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_40_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
    rtimes
    0.38
     Kham
    0.34
     Tamar
    0.34
    ħ
    0.34
     cabinet
    0.33
    තු
    0.33
     dwarf
    0.33
    classed
    0.32
     tamar
    0.32
     ቀ
    0.31
    POSITIVE LOGITS
    ResponseWriter
    0.40
     Foli
    0.36
    createServer
    0.35
    writeObject
    0.34
     continuously
    0.34
    ]/
    0.33
    ]【
    0.33
    WriteString
    0.33
     സൃ
    0.33
     /(
    0.32
    Activations Density 0.005%

    No Known Activations