© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 109777
    Prev
    Next
    INDEX
    Explanations

    नमस्ते greetings + Sanskrit words

    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_2_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
    _
    1.23
    -
    0.96
     posits
    0.89
    ،
    0.89
    "।
    0.88
     over
    0.85
     shale
    0.83
    т
    0.82
    al
    0.82
    ow
    0.80
    POSITIVE LOGITS
    き
    1.07
    t
    0.95
    اك
    0.88
    の前
    0.87
    ூர்
    0.80
    transfected
    0.79
    ್ಯ
    0.77
    اً
    0.77
    dır
    0.77
    に
    0.77
    Activations Density 0.004%

    No Known Activations