© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17283
    Prev
    Next
    INDEX
    Explanations

    customer satisfaction metrics

    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
    вање
    0.40
     ಸಂತ
    0.38
    }?
    0.38
     Equilibrium
    0.38
    Caching
    0.38
     रूपांतर
    0.36
     factoryName
    0.36
    wakilan
    0.36
     disqualify
    0.36
     nut
    0.35
    POSITIVE LOGITS
     technological
    0.41
    Soft
    0.39
    ෝග
    0.39
     Mek
    0.39
    uell
    0.38
     directional
    0.38
    कर्ता
    0.37
    越
    0.37
     Technological
    0.37
    one
    0.36
    Activations Density 0.029%

    No Known Activations