© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39368
    Prev
    Next
    INDEX
    Explanations

    reversing actions

    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_11_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
    ib
    0.60
    -
    0.58
    ્લે
    0.56
    ões
    0.53
    Ņ
    0.53
    istos
    0.52
    侓
    0.52
     bevorzug
    0.50
    ר
    0.50
    letes
    0.49
    POSITIVE LOGITS
    <0xBE>
    0.61
     cerveau
    0.60
     বাকি
    0.58
     kalau
    0.56
     فارسی
    0.56
    อัน
    0.54
     lingerie
    0.54
    ссию
    0.54
    dessous
    0.53
    писать
    0.53
    Activations Density 0.001%

    No Known Activations