© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83705
    Prev
    Next
    INDEX
    Explanations

    closest context

    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_0_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
     echter
    1.22
    ру
    1.21
    "},
    1.13
    "})
    1.11
    يب
    1.06
     unmittelbar
    1.05
     verwand
    1.05
     abgesch
    1.04
    ة
    1.04
     سلي
    1.03
    POSITIVE LOGITS
    ین
    1.93
    ات
    1.59
    is
    1.48
    কে
    1.43
    ت
    1.38
    á
    1.28
    ene
    1.23
    กว่า
    1.23
    ک
    1.21
    อง
    1.18
    Activations Density 0.001%

    No Known Activations