© 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. 28250
    Prev
    Next
    INDEX
    Explanations

    numbers followed by other digits

    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
    ിക്കും
    0.45
     Invent
    0.41
     Leh
    0.40
    丫
    0.39
    aise
    0.37
     காட்சி
    0.37
     Mos
    0.37
     Eisenhower
    0.36
    結
    0.36
     Seems
    0.36
    POSITIVE LOGITS
    def
    0.41
    getattr
    0.39
    ถุนายน
    0.38
     darum
    0.38
     hẹn
    0.38
    rité
    0.38
     parámetro
    0.37
    énées
    0.37
    idade
    0.36
     dose
    0.36
    Activations Density 0.007%

    No Known Activations