© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 134816
    Prev
    Next
    INDEX
    Explanations

    irobot, IR, firo

    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_6_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
    about
    0.48
    inizio
    0.45
    extremely
    0.43
     Мето
    0.43
    زی
    0.43
    nDims
    0.42
    getPath
    0.42
    2
    0.41
    essentially
    0.41
    の開発
    0.41
    POSITIVE LOGITS
     to
    0.71
    ,
    0.49
    ת
    0.48
     nuk
    0.44
     with
    0.42
    টি
    0.41
     aque
    0.41
     exploits
    0.41
    y
    0.41
     lading
    0.41
    Activations Density 0.000%

    No Known Activations