© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103166
    Prev
    Next
    INDEX
    Explanations

    infiltrate

    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_1_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
    I
    1.41
    ,
    1.16
    你
    1.16
    Ii
    1.11
    것
    1.05
    Ps
    1.05
    Ia
    1.05
    you
    1.02
    lies
    1.02
    yta
    1.00
    POSITIVE LOGITS
    是
    1.24
    ي
    1.22
    ።
    1.17
     chandelier
    1.14
     colorless
    1.05
     vermel
    1.05
     carburetor
    1.03
     flammable
    1.02
     materiali
    1.02
     microphone
    1.01
    Activations Density 0.001%

    No Known Activations