© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 233010
    Prev
    Next
    INDEX
    Explanations

    rememberingMethod used: 3

    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_46_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
    uator
    0.36
     oprav
    0.36
    ImageAsset
    0.34
    纹
    0.34
    Musik
    0.34
    ASSERT
    0.33
     Viv
    0.33
    HeaderText
    0.33
    ífer
    0.32
    ㄞ
    0.32
    POSITIVE LOGITS
     یاد
    1.30
     вспом
    1.17
     remembrance
    1.15
     remembering
    1.13
     recall
    1.11
     commemoration
    1.11
     ذكر
    1.10
    纪念
    1.09
     recalling
    1.08
    ذكر
    1.07
    Activations Density 0.049%

    No Known Activations