© 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. 48926
    Prev
    Next
    INDEX
    Explanations

    business model

    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
    Russ
    0.38
    marketing
    0.37
     empresarial
    0.36
    Marketing
    0.35
     البروت
    0.35
    芦
    0.33
    EME
    0.33
     podnik
    0.32
    企业
    0.32
     promoção
    0.32
    POSITIVE LOGITS
     attenu
    0.35
     tett
    0.33
     phone
    0.33
     person
    0.32
     unpleasant
    0.32
     excessively
    0.32
    })/
    0.32
     stenosis
    0.32
     humiliating
    0.32
     पहनी
    0.31
    Activations Density 0.006%

    No Known Activations