© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60837
    Prev
    Next
    INDEX
    Explanations

    actively doing things

    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_11_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
    да
    0.77
     Ши
    0.65
    }$\
    0.64
    ка
    0.62
    کا
    0.61
     દ્વારા
    0.59
    Playback
    0.59
    Load
    0.59
    Dataset
    0.59
    para
    0.58
    POSITIVE LOGITS
    u
    0.86
    in
    0.73
    im
    0.69
     chom
    0.67
     carrots
    0.66
     ido
    0.66
     affections
    0.65
     pregnancies
    0.65
     uncontroll
    0.65
    er
    0.64
    Activations Density 0.005%

    No Known Activations