© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9372
    Prev
    Next
    INDEX
    Explanations

    HR: managers, policies, screening

    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_13_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
    ᵍ
    0.57
     Гинд
    0.53
    는
    0.52
    𝗳
    0.49
    INUS
    0.48
    ⼀
    0.48
    Università
    0.48
    '`
    0.47
    睿
    0.47
     Centres
    0.47
    POSITIVE LOGITS
    )
    0.64
     in
    0.51
     (
    0.51
     materials
    0.50
     )
    0.49
     classifying
    0.49
     och
    0.48
     such
    0.48
    љ
    0.48
     classification
    0.47
    Activations Density 0.023%

    No Known Activations