© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 77350
    Prev
    Next
    INDEX
    Explanations

    suck

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
    ea
    0.41
    dm
    0.39
    omie
    0.38
    閏
    0.38
     Fi
    0.38
    ean
    0.38
    oine
    0.37
     parib
    0.37
    eal
    0.37
    omination
    0.37
    POSITIVE LOGITS
     út
    0.41
    ऊ
    0.39
    Cyt
    0.39
     মৃত্যুর
    0.39
     ო
    0.38
    ụt
    0.38
    𝐗
    0.38
    űt
    0.38
     gehe
    0.37
    枌
    0.37
    Activations Density 0.001%

    No Known Activations