© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 79473
    Prev
    Next
    INDEX
    Explanations

    including but

    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_31_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
    Rag
    0.43
     nerves
    0.41
    ployed
    0.38
    رح
    0.38
    橑
    0.38
    رحب
    0.37
    賴
    0.37
     RISK
    0.36
     indire
    0.36
    笾
    0.36
    POSITIVE LOGITS
     Including
    0.53
    包括
    0.50
    INCLUDING
    0.50
    Including
    0.46
     incluyendo
    0.45
    including
    0.44
     包括
    0.43
     termasuk
    0.43
    รวม
    0.42
     including
    0.42
    Activations Density 0.001%

    No Known Activations