© 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. 36512
    Prev
    Next
    INDEX
    Explanations

    you / find / got

    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
    isa
    0.38
    ère
    0.37
    裁
    0.36
    isions
    0.36
    andel
    0.36
     joueurs
    0.36
    erez
    0.36
    ಡ
    0.36
    arela
    0.35
    azzi
    0.35
    POSITIVE LOGITS
     anything
    0.52
     Anything
    0.49
    Anything
    0.48
    了嗎
    0.46
    ?(
    0.44
     anywhere
    0.43
    了吗
    0.43
    >?
    0.42
    有没有
    0.41
    anything
    0.41
    Activations Density 0.024%

    No Known Activations