© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137514
    Prev
    Next
    INDEX
    Explanations

    dawned / upon / indented / fiords

    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_12_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
    ut
    0.71
    b
    0.62
     It
    0.55
    aza
    0.55
     パン
    0.54
     moistened
    0.53
     b
    0.53
     .
    0.52
    ;
    0.51
    z
    0.51
    POSITIVE LOGITS
    ഴു
    0.53
     Bay
    0.52
    のが
    0.52
     страну
    0.52
     theses
    0.50
     गए
    0.49
    のは
    0.48
    ]}$
    0.48
    NOV
    0.47
     Tez
    0.47
    Activations Density 0.000%

    No Known Activations