© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 50583
    Prev
    Next
    INDEX
    Explanations

    movement towards

    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_55_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
     זו
    0.48
    azole
    0.41
     xếp
    0.41
     esta
    0.40
     Basically
    0.40
     չ
    0.40
    זו
    0.40
     aceasta
    0.38
    विरुद्ध
    0.36
     Projects
    0.36
    POSITIVE LOGITS
    指定
    0.55
     指定
    0.54
    全
    0.49
    指定的
    0.47
     지정
    0.45
    的全
    0.43
    Specified
    0.43
    给定
    0.40
     polymers
    0.39
    を指定
    0.39
    Activations Density 0.001%

    No Known Activations