© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60308
    Prev
    Next
    INDEX
    Explanations

    interior spaces

    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_11_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
     hotel
    0.65
     de
    0.59
     boot
    0.57
     phony
    0.57
     do
    0.56
    るので
    0.56
    );
    0.55
     don
    0.54
    ﻴ
    0.54
    韩国
    0.53
    POSITIVE LOGITS
    xiang
    0.61
    siswa
    0.59
     zwią
    0.59
     veditabbo
    0.59
    ামিটার
    0.57
    akel
    0.57
    चं
    0.55
    낱
    0.55
     विद्यार्थ्या
    0.55
     înviat
    0.54
    Activations Density 0.001%

    No Known Activations