© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 197047
    Prev
    Next
    INDEX
    Explanations

    **modal verb + action verb**

    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_27_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
    шна
    0.35
     tetragonal
    0.34
     から
    0.34
    arier
    0.33
    पतवार
    0.33
    উপর
    0.32
     //=>
    0.32
     অথবা
    0.31
     holocaust
    0.31
     homeschooling
    0.31
    POSITIVE LOGITS
    運営
    0.31
    的人
    0.31
    湆
    0.31
     eseguire
    0.30
     सिल
    0.30
    ಿಕೊಳ್ಳ
    0.29
     Stall
    0.29
    €
    0.29
    seqNum
    0.29
     Nip
    0.29
    Activations Density 0.012%

    No Known Activations