© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 82186
    Prev
    Next
    INDEX
    Explanations

    absorbed narratives or concepts

    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
    1.35
    can
    1.30
    kan
    1.23
     ();
    1.21
    has
    1.20
     август
    1.12
     εν
    1.09
    ர்ச்ச
    1.06
    ስታ
    1.05
     चलता
    1.05
    POSITIVE LOGITS
    :
    1.83
    و
    1.61
    ד
    1.57
    ?
    1.48
    !
    1.46
    ру
    1.41
    ই
    1.40
    ,
    1.39
    ;
    1.39
    {
    1.38
    Activations Density 0.001%

    No Known Activations