© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 204726
    Prev
    Next
    INDEX
    Explanations

    my [possessions or statements]

    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_25_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
     merr
    0.39
     rö
    0.39
     끌
    0.37
     مراسم
    0.37
    ൃശ
    0.37
     mobilization
    0.36
    DU
    0.36
    Cit
    0.36
     Rö
    0.36
     ауди
    0.36
    POSITIVE LOGITS
    বাসী
    0.42
     essendo
    0.41
     experiencing
    0.39
     enfermo
    0.39
     seminal
    0.38
     bhikkhave
    0.38
    বিদেশ
    0.38
    )=[
    0.38
     kecepatan
    0.37
     frugal
    0.37
    Activations Density 0.000%

    No Known Activations