© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 152376
    Prev
    Next
    INDEX
    Explanations

    prepositions/particles

    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_60_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
     on
    0.98
     In
    0.59
     as
    0.58
     or
    0.55
    in
    0.53
     from
    0.50
     IN
    0.47
    一
    0.47
     är
    0.46
    on
    0.46
    POSITIVE LOGITS
    into
    0.89
    在
    0.76
    Into
    0.73
     into
    0.71
    到
    0.70
     इनटू
    0.61
     в
    0.59
     Into
    0.56
    在你
    0.55
     إلى
    0.55
    Activations Density 0.001%

    No Known Activations