© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 88688
    Prev
    Next
    INDEX
    Explanations

    remainder to hide

    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_23_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
    ʡ
    0.37
     цих
    0.35
    환경
    0.34
    च्चय
    0.34
     этих
    0.34
    โร
    0.33
     เช่น
    0.33
    之道
    0.33
     환경
    0.33
    ensibility
    0.33
    POSITIVE LOGITS
     swat
    0.38
     Jr
    0.37
    大家都
    0.36
     சும
    0.35
     F
    0.35
     curb
    0.35
     Khr
    0.35
     Dior
    0.34
     Polit
    0.34
     Eastwood
    0.34
    Activations Density 0.012%

    No Known Activations