© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 249535
    Prev
    Next
    INDEX
    Explanations

    government policies

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     tooth
    1.70
    tooth
    1.53
     Tooth
    1.44
    Tooth
    1.44
     teeth
    1.02
    teeth
    0.94
     diş
    0.92
    歯
    0.90
    牙
    0.90
     Teeth
    0.86
    POSITIVE LOGITS
     statically
    0.42
    prits
    0.39
    િલ
    0.38
    ického
    0.37
    ποιη
    0.37
    ifikat
    0.36
     कच
    0.35
     MACHINERY
    0.35
    িং
    0.34
    ार्टम
    0.34
    Activations Density 0.026%

    No Known Activations