© 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. 109846
    Prev
    Next
    INDEX
    Explanations

    ts followed by specific characters or 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
    ки
    1.36
    ী
    1.34
    ı
    1.27
    ти
    1.19
    િ
    1.18
    них
    1.12
    كز
    1.09
    ம்
    1.07
    ු
    1.07
    м
    1.06
    POSITIVE LOGITS
    1
    1.69
    of
    1.49
    was
    1.24
    .
    1.20
    9
    1.20
     to
    1.15
     \
    1.14
     one
    1.09
    with
    1.09
    5
    1.09
    Activations Density 0.001%

    No Known Activations