© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 139774
    Prev
    Next
    INDEX
    Explanations

    land-grant universities and colleges

    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
     letzte
    0.45
    ଦ
    0.38
     TextEditing
    0.37
     thermometers
    0.36
     laatste
    0.35
     ഹിന്ദു
    0.35
     Bà
    0.35
     Rajya
    0.34
     politischen
    0.33
     increasingly
    0.33
    POSITIVE LOGITS
    ך
    0.35
    Tow
    0.34
    ccgi
    0.34
    Fant
    0.33
    étés
    0.32
    toff
    0.32
    totime
    0.32
    trashItem
    0.32
    tuvo
    0.32
    romino
    0.32
    Activations Density 0.000%

    No Known Activations