© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79251
    Prev
    Next
    INDEX
    Explanations

    teachings of philosophers and religions

    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_0_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
    A
    1.93
    n
    1.72
    ).
    1.71
    ;
    1.70
    ar
    1.68
    l
    1.59
    :
    1.58
    ou
    1.56
    m
    1.50
     an
    1.48
    POSITIVE LOGITS
    し
    1.41
    向け
    1.25
     considerados
    1.20
     proteolytic
    1.18
     confidentialité
    1.17
     básicos
    1.16
     sigue
    1.15
     اینکه
    1.15
    会
    1.15
     desenvolv
    1.11
    Activations Density 0.000%

    No Known Activations