© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14791
    Prev
    Next
    INDEX
    Explanations

    PCIe slots and lanes

    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_15_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
    ӓ
    0.23
     düny
    0.23
     அவர்களின்
    0.22
     FontSize
    0.21
    )】
    0.21
    <unused971>
    0.21
    gbm
    0.21
    ’;
    0.20
     wereld
    0.20
    ,’
    0.20
    POSITIVE LOGITS
    imas
    0.22
    utations
    0.19
     tampering
    0.18
     contamination
    0.18
     modifications
    0.18
     manipulation
    0.18
    起来
    0.17
     altering
    0.17
     tracer
    0.17
    ardia
    0.17
    Activations Density 0.011%

    No Known Activations