© 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. 89845
    Prev
    Next
    INDEX
    Explanations

    corporate business and legal contexts

    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
     поча
    0.55
    ”，
    0.53
     கடுமையான
    0.51
     座
    0.49
    ，”
    0.49
     comenzar
    0.48
     Sitting
    0.48
     armor
    0.48
     oak
    0.47
     його
    0.47
    POSITIVE LOGITS
    스
    0.66
    지
    0.65
    ку
    0.62
    분
    0.61
    자
    0.59
    }^{
    0.58
     XMFLOAT
    0.58
    también
    0.57
    GLISH
    0.56
    tku
    0.55
    Activations Density 0.017%

    No Known Activations