© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120748
    Prev
    Next
    INDEX
    Explanations

    stopping the spread

    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_27_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
     participantes
    0.39
     complejos
    0.37
    PolicyQuery
    0.36
     langsung
    0.35
     ඕ
    0.34
     közvet
    0.34
    Concini
    0.34
     भरतपुर
    0.33
     расту
    0.33
    Krishna
    0.33
    POSITIVE LOGITS
    選
    0.38
     Failure
    0.38
     failure
    0.38
     नाकाम
    0.38
     Caucasian
    0.37
     Faun
    0.37
     ব্যার্থ
    0.35
    จะเป็น
    0.35
     Clean
    0.35
     uncont
    0.34
    Activations Density 0.003%

    No Known Activations