© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 15803
    Prev
    Next
    INDEX
    Explanations

    price alerts and current recommendations

    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_15_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
     emociones
    0.30
     superconductor
    0.29
    Hb
    0.28
    iędzy
    0.27
    bohyd
    0.27
     Technologien
    0.27
    ᠮ
    0.27
     sufrimiento
    0.26
    ේෂ
    0.26
    iligung
    0.26
    POSITIVE LOGITS
     et
    0.33
    érale
    0.31
    VENUE
    0.29
     cou
    0.29
     Coul
    0.28
    venue
    0.28
     "))
    0.28
     Lark
    0.28
    eur
    0.28
     র
    0.27
    Activations Density 0.035%

    No Known Activations