© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 199153
    Prev
    Next
    INDEX
    Explanations

    i, j, k vectors

    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
    ﺘ
    0.57
     don
    0.53
    ்ட்
    0.53
    th
    0.52
    een
    0.52
    standing
    0.50
     ancient
    0.50
     mangrove
    0.50
     position
    0.49
     cutting
    0.49
    POSITIVE LOGITS
     wrześ
    0.61
     Warsz
    0.59
    =
    0.58
    UISelectors
    0.57
     жены
    0.55
     Prendre
    0.55
     Counsel
    0.54
     annihilated
    0.54
     Besar
    0.54
     Autón
    0.54
    Activations Density 0.000%

    No Known Activations