© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38434
    Prev
    Next
    INDEX
    Explanations

    finding literal "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_11_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
    
    0.44
    𝙄
    0.39
    ৬
    0.37
     systému
    0.36
    Მ
    0.36
     lemmas
    0.36
    湋
    0.36
     weaves
    0.35
    ÇÃO
    0.35
    া
    0.35
    POSITIVE LOGITS
    ise
    0.39
    center
    0.37
    rie
    0.37
    head
    0.37
     वी
    0.36
    ures
    0.36
    possible
    0.35
    headed
    0.34
    ase
    0.34
    anza
    0.34
    Activations Density 0.031%

    No Known Activations