© 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. 14426
    Prev
    Next
    INDEX
    Explanations

    serial number

    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
    StudentNo
    0.15
     چال
    0.15
    alted
    0.15
    ^*(\
    0.14
    ata
    0.14
    پے
    0.14
     stesse
    0.14
     destra
    0.14
     Cartesian
    0.14
     satire
    0.14
    POSITIVE LOGITS
    Om
    0.15
    (
    0.15
    ôm
    0.14
    ้ม
    0.13
     miljoen
    0.13
    彿
    0.13
    रो
    0.13
     โอ
    0.13
     পাট
    0.13
     Omb
    0.13
    Activations Density 0.009%

    No Known Activations