© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 170650
    Prev
    Next
    INDEX
    Explanations

    communication

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    isph
    0.40
    isch
    0.34
     اقول
    0.34
    隀
    0.34
    Abstract
    0.33
     vòng
    0.33
    মিস
    0.33
    𝗌
    0.33
     технологі
    0.33
    কাতার
    0.33
    POSITIVE LOGITS
     commun
    0.64
     Commun
    0.59
     comun
    0.58
     trans
    0.55
     kommun
    0.51
     komun
    0.51
    Commun
    0.50
     Comun
    0.50
     communic
    0.47
     Comm
    0.47
    Activations Density 0.000%

    No Known Activations