© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 46998
    Prev
    Next
    INDEX
    Explanations

    underserved audiences, communities, markets, niches

    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_10_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
    :
    0.68
    ὃ
    0.65
     what
    0.62
     lồ
    0.62
    如何
    0.61
    Якщо
    0.59
     milyen
    0.59
    Ꮠ
    0.59
    𝗦
    0.59
     ನಾನು
    0.58
    POSITIVE LOGITS
    m
    0.79
    ्ज
    0.64
    puri
    0.63
    p
    0.63
    купа
    0.62
    ла
    0.60
     sociaux
    0.59
    were
    0.58
     atvej
    0.58
    רים
    0.58
    Activations Density 0.006%

    No Known Activations