© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159144
    Prev
    Next
    INDEX
    Explanations

    redacted

    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_2_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
    ي
    1.45
    ра
    1.13
    dır
    1.10
    يلي
    1.08
    dı
    1.07
    durch
    1.02
    ка
    1.02
    ла
    1.02
    يلا
    1.00
    ва
    0.99
    POSITIVE LOGITS
    .
    1.48
     you
    1.18
    وا
    1.15
    ored
    1.13
    ation
    1.10
    ote
    1.10
     the
    1.09
     is
    1.09
    ide
    1.08
    I
    1.05
    Activations Density 0.000%

    No Known Activations