© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 154792
    Prev
    Next
    INDEX
    Explanations

    Av / Bit

    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
     ом
    0.42
    悸
    0.40
    वाई
    0.39
    Sach
    0.38
     बाली
    0.37
     ಬೆಳ
    0.37
     гри
    0.37
     syring
    0.36
     Palms
    0.36
    拟
    0.36
    POSITIVE LOGITS
    orer
    0.45
     Av
    0.44
    sia
    0.44
     av
    0.43
    Av
    0.41
     bit
    0.40
    nia
    0.39
    REEN
    0.39
    bit
    0.39
    Bit
    0.39
    Activations Density 0.000%

    No Known Activations