© 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. 32278
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with fractions and limits

    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
    ட்சத்திர
    0.38
    puzzle
    0.37
     coping
    0.35
    魚
    0.35
     zero
    0.34
    DeleteDialogOpen
    0.34
     ok
    0.33
     bip
    0.33
    恁
    0.33
     Voice
    0.32
    POSITIVE LOGITS
    Wa
    0.36
    郁
    0.36
    Fi
    0.33
    ]=="
    0.33
    IZATION
    0.33
    +="
    0.33
    Vectorizer
    0.33
    opoe
    0.32
    enian
    0.32
    jResponse
    0.32
    Activations Density 0.004%

    No Known Activations