© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14419
    Prev
    Next
    INDEX
    Explanations

    actions and states ending in 'ing'

    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_15_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
    ll
    0.25
    oe
    0.23
    r
    0.23
    l
    0.23
    oi
    0.22
    omeness
    0.21
    oo
    0.21
    one
    0.21
    itel
    0.21
    1
    0.21
    POSITIVE LOGITS
    ស្រ
    0.20
     giphy
    0.20
     উল্লেখিত
    0.20
    ئے
    0.20
     গুগল
    0.20
     سال
    0.19
     executions
    0.19
    UpdateButton
    0.19
     梅
    0.19
     evaluations
    0.19
    Activations Density 0.064%

    No Known Activations