© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 5931
    Prev
    Next
    INDEX
    Explanations

    0

    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_44_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
    Amy
    0.37
     Grove
    0.37
     Borrow
    0.37
    ঘর
    0.36
    祠
    0.35
     percorso
    0.35
     stalled
    0.35
    blastoma
    0.35
    Grove
    0.35
     مسیر
    0.34
    POSITIVE LOGITS
    σία
    0.40
     Kih
    0.39
    aughan
    0.38
     OCT
    0.37
    ੀ
    0.37
     Nair
    0.36
     Penalty
    0.36
    emans
    0.34
     Kitts
    0.34
     කිය
    0.34
    Activations Density 0.009%

    No Known Activations