© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 204538
    Prev
    Next
    INDEX
    Explanations

    focus on

    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_25_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
    libc
    0.39
    嬌
    0.39
    derive
    0.38
    isi
    0.37
    娇
    0.37
     Kern
    0.36
     Late
    0.35
     veya
    0.35
     Bä
    0.34
    label
    0.34
    POSITIVE LOGITS
     telescope
    0.38
     এইরূপে
    0.38
     乀
    0.38
     intérêts
    0.38
     endothelium
    0.38
     potp
    0.38
     interacts
    0.38
     trousers
    0.38
     максимум
    0.38
     immortality
    0.37
    Activations Density 0.010%

    No Known Activations