© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 205089
    Prev
    Next
    INDEX
    Explanations

    poetry and phrases

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     dear
    0.46
     ea
    0.39
     warring
    0.39
     pół
    0.39
     करीना
    0.39
     Sorrent
    0.38
    𝓎
    0.38
     Morrow
    0.38
     inhe
    0.37
     Shea
    0.37
    POSITIVE LOGITS
    >(
    0.45
     сердце
    0.39
    }:$
    0.39
     Schwester
    0.39
     douceur
    0.39
    愛
    0.39
    Silent
    0.38
     Designation
    0.38
    Heart
    0.38
     قلب
    0.38
    Activations Density 0.014%

    No Known Activations