© 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. 166623
    Prev
    Next
    INDEX
    Explanations

    asking questions

    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
     familiarize
    0.45
     clarified
    0.44
     clarification
    0.44
     explanation
    0.43
     被
    0.41
     activated
    0.40
     reactivation
    0.40
     answer
    0.40
     beantwort
    0.40
     outline
    0.40
    POSITIVE LOGITS
    valence
    0.39
    Ή
    0.38
     Ern
    0.38
    Là
    0.36
    स्पेक्टर
    0.36
    欣
    0.36
    ั่น
    0.35
     ευ
    0.35
     Нет
    0.35
     있었습니다
    0.35
    Activations Density 0.004%

    No Known Activations