© 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. 161895
    Prev
    Next
    INDEX
    Explanations

    they followed by verb

    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
    ⵄ
    0.38
     kup
    0.37
     committed
    0.35
     poumon
    0.35
    ArgsConstructor
    0.35
    {\"
    0.34
     gestellt
    0.34
    ادة
    0.33
     vê
    0.33
     sekt
    0.33
    POSITIVE LOGITS
    ליך
    0.40
     Daylight
    0.39
     عليك
    0.39
    興趣
    0.38
    汝
    0.38
     Samstag
    0.36
     مقابلے
    0.36
    वाही
    0.36
     توهان
    0.36
     বজ্র
    0.36
    Activations Density 0.001%

    No Known Activations