© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 134221
    Prev
    Next
    INDEX
    Explanations

    wheezing

    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_1_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
    ﻋ
    1.44
    ﺑ
    1.35
    ﺪ
    1.34
    ﻗ
    1.27
    ﻫ
    1.26
     effectuées
    1.24
     ﺍﻟ
    1.23
     ሁሉም
    1.23
    ᱘
    1.23
    ᱒
    1.22
    POSITIVE LOGITS
    د
    1.80
    ש
    1.47
    就
    1.45
    ش
    1.40
    u
    1.32
    ö
    1.31
    of
    1.30
    रा
    1.30
    ي
    1.27
    ü
    1.26
    Activations Density 0.000%

    No Known Activations