© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7006
    Prev
    Next
    INDEX
    Explanations

    Angular modules and browser imports

    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_39_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
     Robles
    0.46
     Agile
    0.40
     Carlos
    0.39
     kr
    0.39
     Rolling
    0.39
    ournal
    0.39
    兹
    0.39
     GB
    0.38
     agile
    0.38
     vx
    0.38
    POSITIVE LOGITS
    foregroundColor
    0.44
    Formatter
    0.38
     residue
    0.38
    pett
    0.37
    resid
    0.37
    pard
    0.37
    Upper
    0.36
    hatt
    0.36
    Browser
    0.36
     Jenner
    0.35
    Activations Density 0.001%

    No Known Activations