© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 28017
    Prev
    Next
    INDEX
    Explanations

    price and configuration difference

    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_40_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
     formic
    0.40
     intercept
    0.39
     MATRIX
    0.39
    ceiver
    0.38
    煩
    0.37
    కే
    0.36
    扰
    0.36
     添加
    0.35
     Gespräch
    0.35
     Val
    0.35
    POSITIVE LOGITS
     رای
    0.41
     pith
    0.39
     ray
    0.37
    eline
    0.37
    हूं
    0.35
     wind
    0.35
    Buttons
    0.34
    zęd
    0.34
     peinture
    0.34
    ждения
    0.33
    Activations Density 0.013%

    No Known Activations