© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242999
    Prev
    Next
    INDEX
    Explanations

    Lincoln Memorial and Park

    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_40_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
    opr
    0.49
    president
    0.39
    avez
    0.37
    ﺛ
    0.37
    洊
    0.36
     президент
    0.36
    Sono
    0.36
    ≜
    0.35
    મે
    0.35
    їв
    0.35
    POSITIVE LOGITS
     লো
    0.40
     sands
    0.40
     races
    0.38
     rays
    0.38
     Loud
    0.37
     lot
    0.37
     ray
    0.37
     trọng
    0.37
     rul
    0.36
     softening
    0.36
    Activations Density 0.001%

    No Known Activations