© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 180993
    Prev
    Next
    INDEX
    Explanations

    The Trevor Project

    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_24_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
    chanical
    0.36
     failed
    0.36
    ಚಾರ
    0.34
     زین
    0.33
     fortress
    0.33
     javax
    0.33
     manor
    0.33
    ح
    0.33
    V
    0.32
     drew
    0.32
    POSITIVE LOGITS
     مربوط
    0.40
     прод
    0.39
     Dermatology
    0.38
     കൂടുത
    0.36
     infert
    0.36
     EVs
    0.36
     косми
    0.36
     огром
    0.36
    mobilpay
    0.36
    बार
    0.35
    Activations Density 0.040%

    No Known Activations