© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103284
    Prev
    Next
    INDEX
    Explanations

    bandwidth constraints, management, savings, costs

    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_1_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
     as
    1.01
    都
    0.98
    開始
    0.98
    ス
    0.95
    с
    0.92
    不
    0.90
    出
    0.89
    受信
    0.89
    高
    0.88
    ется
    0.87
    POSITIVE LOGITS
    and
    1.56
    at
    1.38
    ag
    1.31
    am
    1.25
    ik
    1.24
    h
    1.21
    ai
    1.17
    ال
    1.11
    l
    1.11
    ಾ
    1.10
    Activations Density 0.000%

    No Known Activations