© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 177382
    Prev
    Next
    INDEX
    Explanations

    technical specifications

    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_50_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
     Four
    2.34
    Four
    2.34
    四
    2.28
     four
    2.20
    four
    2.14
     FOUR
    2.08
    FOUR
    2.02
     四
    1.96
     dört
    1.92
     quatro
    1.91
    POSITIVE LOGITS
    නය
    0.35
    ႅ
    0.35
     ख़
    0.34
    ್ಟ
    0.34
    ospin
    0.33
    ლების
    0.33
    ਨਾ
    0.32
    ല്ലാത്ത
    0.32
    வல்
    0.31
    iefert
    0.31
    Activations Density 0.145%

    No Known Activations