© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 79894
    Prev
    Next
    INDEX
    Explanations

    internal access and private methods

    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_31_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
    廣告
    0.39
     价
    0.38
     aparecen
    0.37
     사람이
    0.36
     富
    0.36
     сві
    0.35
    PrintError
    0.35
    伟大
    0.35
     tomb
    0.35
     магазина
    0.35
    POSITIVE LOGITS
     internals
    0.47
    internal
    0.44
    友
    0.44
    udas
    0.43
     secrecy
    0.41
    Friend
    0.39
    knowledge
    0.39
     internal
    0.38
    private
    0.38
    Internal
    0.38
    Activations Density 0.120%

    No Known Activations