© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 37729
    Prev
    Next
    INDEX
    Explanations

    Manmohan Singh and manpower

    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
    படுத்த
    0.64
    '
    0.62
     })_{
    0.60
    ۳
    0.60
    ۹
    0.59
    ៤
    0.59
    SPEED
    0.58
    િત
    0.57
     дизай
    0.56
    >
    0.56
    POSITIVE LOGITS
    м
    0.91
    म
    0.88
    م
    0.88
    가
    0.86
    ن
    0.80
    로
    0.79
    ,
    0.79
    ul
    0.78
    in
    0.74
    ام
    0.73
    Activations Density 0.000%

    No Known Activations