© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 204751
    Prev
    Next
    INDEX
    Explanations

    for

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     meaningless
    0.36
     են
    0.36
    키
    0.36
    Ⲏ
    0.35
     اضافہ
    0.35
     pointless
    0.34
     स्वी
    0.34
    োধী
    0.34
    klasse
    0.33
     無
    0.33
    POSITIVE LOGITS
     relaxation
    0.42
    relaxation
    0.41
     Expect
    0.37
     Liberty
    0.37
     liberty
    0.37
    uración
    0.36
     relax
    0.36
     apaixon
    0.36
     Relaxation
    0.35
     Forget
    0.35
    Activations Density 0.001%

    No Known Activations