© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 60002
    Prev
    Next
    INDEX
    Explanations

    "ro" followed by "les"

    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_2_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
    u
    2.00
    i
    1.63
    er
    1.48
    an
    1.48
    and
    1.40
    ik
    1.40
    as
    1.38
    uk
    1.34
    ized
    1.33
    :
    1.33
    POSITIVE LOGITS
     في
    1.77
    在
    1.77
     в
    1.60
     in
    1.38
     σε
    1.38
    も
    1.37
    もら
    1.31
     در
    1.25
     crescita
    1.20
    ও
    1.14
    Activations Density 0.001%

    No Known Activations