© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 229306
    Prev
    Next
    INDEX
    Explanations

    "-ite" suffix

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
     edin
    1.02
    edin
    0.65
     Edin
    0.64
     দিন
    0.57
    吧
    0.55
     давайте
    0.53
     Давайте
    0.48
    вайте
    0.48
    irin
    0.47
     كن
    0.46
    POSITIVE LOGITS
    ite
    0.58
    ж
    0.57
    enite
    0.53
     드
    0.52
    nite
    0.51
    Fact
    0.49
    ните
    0.49
    ITE
    0.49
    mite
    0.48
    ilites
    0.48
    Activations Density 0.001%

    No Known Activations