© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26068
    Prev
    Next
    INDEX
    Explanations

    if not

    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_10_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
     are
    0.37
    ि
    0.25
    к
    0.23
    ெ
    0.23
    ين
    0.22
    A
    0.22
    ía
    0.21
    ano
    0.21
    ே
    0.21
    ג
    0.20
    POSITIVE LOGITS
    t
    0.27
    (
    0.23
    to
    0.23
    ModelGrid
    0.23
    tumor
    0.22
     diferenciar
    0.22
     배치
    0.22
    them
    0.21
    setColor
    0.21
    他
    0.21
    Activations Density 0.009%

    No Known Activations