© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91518
    Prev
    Next
    INDEX
    Explanations

    One Russian, OneToOne, Hundred Years, Knee

    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_3_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
    ekten
    0.64
    ator
    0.63
    اه
    0.62
    哽
    0.62
    ស
    0.62
    ation
    0.60
    Er
    0.60
    ieren
    0.60
     दल
    0.60
    :
    0.58
    POSITIVE LOGITS
    ר
    1.02
    ર
    0.98
    ری
    0.95
    titulo
    0.93
    р
    0.93
    ু
    0.92
     untrue
    0.91
    ва
    0.90
    tit
    0.90
    لین
    0.90
    Activations Density 0.003%

    No Known Activations