© 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. 31852
    Prev
    Next
    INDEX
    Explanations

    private fun

    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
    Ꭶ
    0.40
     फिल्
    0.39
    და
    0.38
     reimburse
    0.38
    amas
    0.38
     ट्रैक
    0.37
     ট্র্যাক
    0.37
     య
    0.37
     איך
    0.37
     abierta
    0.36
    POSITIVE LOGITS
     private
    0.55
    Private
    0.47
     Private
    0.47
    PRIVATE
    0.47
     susp
    0.44
     privata
    0.44
     PRIVATE
    0.43
     privada
    0.42
     privat
    0.42
    private
    0.41
    Activations Density 0.000%

    No Known Activations