© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 905
    Prev
    Next
    INDEX
    Explanations

    position indicators

    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_44_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
    GUID
    0.39
    変
    0.38
    Kum
    0.37
    אל
    0.36
     зло
    0.36
     GUIDE
    0.36
    MORE
    0.36
    আস
    0.36
    開放
    0.36
    нику
    0.35
    POSITIVE LOGITS
     i
    0.46
     karen
    0.42
     j
    0.38
     Foreground
    0.38
     फोर
    0.37
    ʲ
    0.37
     pesso
    0.37
     cei
    0.36
    i
    0.36
     Dou
    0.35
    Activations Density 0.133%

    No Known Activations