© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 5614
    Prev
    Next
    INDEX
    Explanations

    purposeoperatinginformationdependent

    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_40_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
     закона
    0.21
     seeded
    0.19
     seeding
    0.18
    bentuk
    0.17
    фу
    0.17
    seeded
    0.17
    傅
    0.17
    迲
    0.17
     Seed
    0.17
    embedded
    0.17
    POSITIVE LOGITS
     ulcers
    0.19
    IBRARY
    0.19
     headaches
    0.18
     patriotic
    0.18
     হারাম
    0.18
     Lutheran
    0.17
     medicare
    0.17
     dieting
    0.17
     चतुर्थ
    0.17
    קור
    0.17
    Activations Density 0.016%

    No Known Activations