© 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. 13914
    Prev
    Next
    INDEX
    Explanations

    you followed by verbs

    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
     encounters
    0.33
     jd
    0.29
     encounter
    0.28
    遇
    0.28
    romat
    0.28
     ब्रि
    0.27
     encountering
    0.27
     worth
    0.26
    órico
    0.26
     Barca
    0.26
    POSITIVE LOGITS
    VELOP
    0.26
    늡
    0.25
     Visible
    0.25
     podm
    0.24
    궐
    0.24
    ]")
    0.24
    linewidth
    0.23
    تع
    0.23
     Standort
    0.23
    まった
    0.23
    Activations Density 0.060%

    No Known Activations