© 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. 204555
    Prev
    Next
    INDEX
    Explanations

    discussing tastes or preferences

    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
     lifelong
    0.22
    coverageStat
    0.21
    につきまして
    0.20
    hened
    0.20
    嬉
    0.20
     দৃষ্টিভ
    0.19
    喜爱
    0.19
    hobby
    0.19
    หมือน
    0.18
     ஆதர
    0.18
    POSITIVE LOGITS
     số
    0.20
    ﻕ
    0.19
     Pisc
    0.19
     Dw
    0.19
     Dok
    0.19
     P
    0.18
     checking
    0.18
    راز
    0.18
     SAL
    0.18
     আদাল
    0.18
    Activations Density 0.004%

    No Known Activations