© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 258147
    Prev
    Next
    INDEX
    Explanations

    privacy settings and security

    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_22_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
     κάν
    0.45
    力
    0.41
     noção
    0.41
     શક્ય
    0.39
    传
    0.38
     dxe
    0.38
     dễ
    0.38
    XXXXXXXX
    0.38
    
    0.38
    并行
    0.38
    POSITIVE LOGITS
    ূপ
    0.41
     সি
    0.39
    label
    0.36
    sobre
    0.36
    circa
    0.36
    सिर
    0.36
    compile
    0.36
    hindi
    0.36
    youtu
    0.35
    ঘ্রই
    0.35
    Activations Density 0.001%

    No Known Activations