© 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. 31937
    Prev
    Next
    INDEX
    Explanations

    watch over or protect

    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
    oys
    0.38
     એપ્
    0.35
    ósfera
    0.35
    izdat
    0.35
    Edd
    0.35
     Eddy
    0.35
    ophysics
    0.35
    ="#{
    0.35
    haft
    0.34
    apia
    0.34
    POSITIVE LOGITS
     guardian
    1.73
     Guardian
    1.58
    Guardian
    1.52
    guardian
    1.51
     protector
    1.44
     guardians
    1.39
     protectors
    1.34
    保护
    1.32
     protect
    1.27
     Protector
    1.27
    Activations Density 0.030%

    No Known Activations