© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 14282
    Prev
    Next
    INDEX
    Explanations

    Code input and structure

    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_34_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
     tangente
    0.38
    タリー
    0.37
     sket
    0.36
    व्यू
    0.36
     схе
    0.36
    哽
    0.34
    ේ
    0.34
     крат
    0.34
    тики
    0.33
     Clubhouse
    0.33
    POSITIVE LOGITS
     ಸಲ್ಲ
    0.47
     Write
    0.46
    William
    0.43
    Write
    0.41
    首
    0.41
    Label
    0.39
     label
    0.39
     William
    0.39
     write
    0.38
    Tex
    0.38
    Activations Density 0.148%

    No Known Activations