© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206236
    Prev
    Next
    INDEX
    Explanations

    ISBN lists and metadata

    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_20_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
    ciò
    0.13
     Spagna
    0.12
     esattamente
    0.12
     eight
    0.12
    !
    0.12
     version
    0.12
    version
    0.12
     hoffe
    0.12
     maximus
    0.12
    ๆ
    0.12
    POSITIVE LOGITS
    gulation
    0.13
    𝚄
    0.13
    BLINK
    0.13
    kot
    0.12
    estimators
    0.12
    زور
    0.12
    OGRAM
    0.12
    正则
    0.12
     السيد
    0.12
    颚
    0.12
    Activations Density 0.000%

    No Known Activations