© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13761
    Prev
    Next
    INDEX
    Explanations

    seeking connection

    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_13_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
     \
    0.35
    يدة
    0.34
     phổ
    0.34
     yöntem
    0.33
    ен
    0.32
     ocor
    0.32
    睪
    0.32
     पद्ध
    0.32
     *\
    0.32
     populer
    0.32
    POSITIVE LOGITS
    Honda
    0.38
     Cardiac
    0.38
     Relations
    0.35
     NOAA
    0.35
     Attorneys
    0.35
    llvm
    0.35
     Cognitive
    0.34
    modulation
    0.34
    Science
    0.34
    හු
    0.34
    Activations Density 0.088%

    No Known Activations