© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 78862
    Prev
    Next
    INDEX
    Explanations

    me

    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
    nti
    0.38
    quarters
    0.37
     какво
    0.37
     quarters
    0.37
     ")[
    0.36
    "});
    0.36
     पवित्र
    0.35
    zky
    0.35
     পার্ব
    0.34
    cem
    0.34
    POSITIVE LOGITS
     HER
    0.65
     THERE
    0.60
    HER
    0.55
     THIS
    0.52
     THESE
    0.52
     THAT
    0.51
    HERE
    0.49
     Т
    0.47
     HE
    0.47
    THERE
    0.47
    Activations Density 0.004%

    No Known Activations