© 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. 161650
    Prev
    Next
    INDEX
    Explanations

    language model

    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
    量
    0.32
    lery
    0.30
     poslov
    0.30
    业协会
    0.30
    houd
    0.29
    牪
    0.29
    ience
    0.29
    boden
    0.29
    eur
    0.28
    铄
    0.28
    POSITIVE LOGITS
     mint
    0.32
     Healing
    0.29
     created
    0.28
    EDES
    0.28
     immig
    0.27
    ისი
    0.27
    unde
    0.27
    ⠿
    0.27
     контро
    0.26
     bxa
    0.26
    Activations Density 0.016%

    No Known Activations