© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 89486
    Prev
    Next
    INDEX
    Explanations

    video component, viewers, listeners, audiences

    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_23_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
     trends
    0.39
     doubling
    0.39
     alterar
    0.37
     новости
    0.37
     Asking
    0.37
    夫
    0.36
     ur
    0.36
     doubled
    0.36
     obligé
    0.35
     kula
    0.35
    POSITIVE LOGITS
    God
    0.35
     audiences
    0.34
    观众
    0.34
     응
    0.34
    DialogOpen
    0.33
     വീഡിയോ
    0.33
     Greenland
    0.32
     వీడియో
    0.32
    ராட்ச
    0.32
     구독
    0.32
    Activations Density 0.014%

    No Known Activations