© 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. 82945
    Prev
    Next
    INDEX
    Explanations

    locations and addresses

    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
     สม
    0.41
    ARRY
    0.40
    zab
    0.38
     온
    0.38
    㢄
    0.36
    不要
    0.36
    ടുത
    0.36
    ഡ്
    0.35
    ับสน
    0.35
     앱
    0.35
    POSITIVE LOGITS
     Marvin
    0.43
     Barlow
    0.42
     knot
    0.41
     rifle
    0.38
     rifles
    0.38
     Barnard
    0.38
     eff
    0.37
     Slavic
    0.37
     calyce
    0.37
     cannon
    0.37
    Activations Density 0.000%

    No Known Activations