© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79264
    Prev
    Next
    INDEX
    Explanations

    From the equation

    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_0_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
    지
    1.75
    ामध्ये
    1.41
    কে
    1.34
    den
    1.34
    ды
    1.30
    ді
    1.30
    ם
    1.30
    اک
    1.27
    ز
    1.23
    ку
    1.21
    POSITIVE LOGITS
     for
    1.59
     at
    1.59
     on
    1.56
    0
    1.34
     recib
    1.13
     are
    1.09
     loses
    1.09
     erreichte
    1.07
    К
    1.05
     يق
    1.05
    Activations Density 0.004%

    No Known Activations