© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 209599
    Prev
    Next
    INDEX
    Explanations

    coding setup

    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_10_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
    st
    0.21
    ק
    0.20
    ם
    0.20
    н
    0.18
    s
    0.18
    ia
    0.18
    ሚያ
    0.17
    sa
    0.17
    0.16
    ambarkan
    0.16
    POSITIVE LOGITS
     vf
    0.21
     majú
    0.21
     o
    0.20
     ceremonies
    0.20
     lê
    0.19
     bunkers
    0.19
    鯤
    0.19
     großen
    0.19
     Küh
    0.19
     biot
    0.19
    Activations Density 0.004%

    No Known Activations