© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 164225
    Prev
    Next
    INDEX
    Explanations

    maximum, largest, location, encoder, gradients

    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_13_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
    os
    0.26
    یک
    0.25
    em
    0.24
    ０
    0.23
    ை
    0.23
    response
    0.22
     کررہے
    0.22
    acceptable
    0.22
    ުރ
    0.22
    rate
    0.22
    POSITIVE LOGITS
     والاح
    0.22
     расши
    0.22
    愎
    0.22
     gcd
    0.21
     Tournament
    0.20
    gern
    0.20
     Improves
    0.20
     Propositions
    0.20
     যেকোনো
    0.20
     cus
    0.20
    Activations Density 0.016%

    No Known Activations