© 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. 141541
    Prev
    Next
    INDEX
    Explanations

    academic achievement

    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
     pets
    0.42
    g
    0.41
    Pets
    0.41
     lagoons
    0.40
     ולה
    0.40
    damaged
    0.40
     śred
    0.39
    ؛
    0.39
    dogs
    0.38
    ✼
    0.38
    POSITIVE LOGITS
     Appropriations
    0.45
     Court
    0.40
    裨
    0.39
     Cour
    0.38
     HHS
    0.38
     Naval
    0.38
     $(".
    0.38
    ன்மையான
    0.38
     JP
    0.38
     కుమార్
    0.37
    Activations Density 0.000%

    No Known Activations