© 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. 109937
    Prev
    Next
    INDEX
    Explanations

    for + noun/adverbial phrase

    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
     It
    1.40
    t
    1.28
     an
    1.26
    _
    1.24
     it
    1.20
    í
    1.18
    \
    1.13
    d
    1.06
    ᆼ
    1.06
    き
    1.03
    POSITIVE LOGITS
    in
    1.63
    ak
    1.10
    ,
    1.10
    ться
    1.09
    ↵
    1.04
    的同时
    1.00
    ین
    0.96
    ’
    0.96
    ක්
    0.95
    ेंस
    0.95
    Activations Density 0.000%

    No Known Activations