© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42233
    Prev
    Next
    INDEX
    Explanations

    numerical identifiers and code snippets

    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_22_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
    dont
    0.24
    plan
    0.24
    don
    0.24
     Colonies
    0.23
     겁
    0.23
    ర్‌
    0.22
     সর্বদা
    0.22
    éra
    0.22
     comunes
    0.22
    cz
    0.22
    POSITIVE LOGITS
     Moritz
    0.26
    CartVO
    0.26
     weave
    0.26
     quatro
    0.25
    ولة
    0.25
     overturn
    0.25
    Kết
    0.25
     intensively
    0.25
    Какой
    0.25
    簟
    0.25
    Activations Density 0.009%

    No Known Activations