© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 143522
    Prev
    Next
    INDEX
    Explanations

    hypothesized outcomes and impacts

    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
    u
    1.46
    dır
    1.38
    ל
    1.27
    é
    1.26
    нг
    1.23
    .
    1.21
    larda
    1.20
    اء
    1.19
    תר
    1.18
    ل
    1.16
    POSITIVE LOGITS
     in
    1.85
     for
    1.61
    ک
    1.36
    ة
    1.34
     that
    1.30
    ும்
    1.27
    িয়ে
    1.26
    ING
    1.25
    Amerika
    1.23
    ية
    1.23
    Activations Density 0.000%

    No Known Activations