© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 182931
    Prev
    Next
    INDEX
    Explanations

    whether followed by it, you, or I

    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_29_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
     duquel
    0.38
     referencia
    0.37
     Features
    0.37
     #####
    0.37
     اوپر
    0.37
     ###
    0.36
    숟
    0.36
     grasa
    0.35
     Recomend
    0.35
     aluminio
    0.34
    POSITIVE LOGITS
    House
    0.43
    हायला
    0.39
    𝙫
    0.39
     وضعیت
    0.38
    evolving
    0.37
    बिट
    0.36
    חו
    0.36
     ಹಲ
    0.36
     Siv
    0.36
    дом
    0.35
    Activations Density 0.000%

    No Known Activations