© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 32575
    Prev
    Next
    INDEX
    Explanations

    numbers or counts

    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_40_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
     nine
    0.92
    nine
    0.84
    九
    0.79
     Nine
    0.75
     eight
    0.75
    Nine
    0.75
     девя
    0.75
     nueve
    0.73
    eight
    0.72
    第九
    0.70
    POSITIVE LOGITS
     Five
    0.71
     Four
    0.69
    五
    0.65
    Four
    0.65
    FIVE
    0.64
    Five
    0.63
     FIVE
    0.63
     four
    0.59
     пя
    0.58
     四
    0.57
    Activations Density 0.078%

    No Known Activations