© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35604
    Prev
    Next
    INDEX
    Explanations

    aluminum

    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_11_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
    ,
    0.40
    '
    0.38
     পাকা
    0.32
    ’
    0.32
    HE
    0.32
    רים
    0.31
    isierten
    0.31
    ված
    0.31
    ing
    0.30
    ارى
    0.30
    POSITIVE LOGITS
     Does
    0.40
     Neigh
    0.38
     Neighbour
    0.37
    odikwa
    0.37
     ODM
    0.37
    िडेट
    0.36
     "]");
    0.36
     ل
    0.36
     Sul
    0.35
     Dish
    0.35
    Activations Density 0.001%

    No Known Activations