© 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. 9557
    Prev
    Next
    INDEX
    Explanations

    independence, charming, generous

    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
    ight
    0.62
    s
    0.58
    zuk
    0.55
    ink
    0.53
    so
    0.52
    well
    0.52
    ric
    0.52
    sl
    0.51
    imi
    0.51
    "
    0.51
    POSITIVE LOGITS
     angustato
    0.55
     prosecuting
    0.54
    нены
    0.53
    άρ
    0.52
     Importantly
    0.52
    𒆠
    0.52
     semuanya
    0.51
     nemo
    0.51
    ِی
    0.49
    ర్టు
    0.49
    Activations Density 0.132%

    No Known Activations