© 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. 159480
    Prev
    Next
    INDEX
    Explanations

    uptrend, uptown, uptight, upturn

    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
     in
    1.31
    ை
    1.30
    х
    1.13
    il
    1.10
    ट
    1.09
    তা
    1.08
     categor
    1.08
    ва
    1.07
    ul
    1.05
     by
    1.05
    POSITIVE LOGITS
    f
    1.32
    ：
    1.30
    It
    1.22
    the
    1.16
    、
    1.16
    0
    1.16
    س
    1.13
    ců
    1.13
    to
    1.10
    ０
    1.09
    Activations Density 0.000%

    No Known Activations