© 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. 27041
    Prev
    Next
    INDEX
    Explanations

    option, spaghetti, author

    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
    ATUS
    0.36
    ammans
    0.35
     ಹೊರ
    0.33
    Und
    0.32
    mités
    0.32
    십
    0.32
     Municipal
    0.31
    mité
    0.31
    phase
    0.31
    രണം
    0.31
    POSITIVE LOGITS
     closest
    0.35
     instruction
    0.34
     Viator
    0.33
     willing
    0.33
     sweetheart
    0.33
     ranging
    0.33
    듯
    0.33
    രോ
    0.32
    {\"
    0.32
    𝘁
    0.32
    Activations Density 0.401%

    No Known Activations