© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 176456
    Prev
    Next
    INDEX
    Explanations

    runs when script executed directly

    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_20_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
     එය
    0.33
     axios
    0.29
     l
    0.28
     combustion
    0.28
    ogon
    0.27
     thwart
    0.27
     by
    0.27
     biogas
    0.26
     thorax
    0.26
     Feuer
    0.26
    POSITIVE LOGITS
     informação
    0.31
    ллі
    0.29
    stev
    0.28
    lend
    0.28
    eqn
    0.28
    maybe
    0.28
    📆
    0.28
    प्टेंबर
    0.27
    gene
    0.27
    Você
    0.27
    Activations Density 0.004%

    No Known Activations