© 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. 45132
    Prev
    Next
    INDEX
    Explanations

    Possessions, fillets, listing, rocks

    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
    b
    0.53
     de
    0.50
    𝑡
    0.50
    ამ
    0.49
    ን
    0.48
    al
    0.47
    Whe
    0.47
     WF
    0.46
     École
    0.46
    B
    0.46
    POSITIVE LOGITS
    력
    0.49
    랑
    0.48
     seeming
    0.47
     watery
    0.47
     Messaging
    0.47
     مگر
    0.45
     fantastical
    0.45
     senseless
    0.44
     simpel
    0.43
     প্রতিক্রি
    0.43
    Activations Density 0.000%

    No Known Activations