© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 181032
    Prev
    Next
    INDEX
    Explanations

    depends on

    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_24_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
    !='')
    0.15
    PlatformImage
    0.14
    र्गत
    0.14
    Profiler
    0.14
     ਨੇ
    0.14
    :>
    0.14
     నొప్పి
    0.13
    欽
    0.13
     일부
    0.13
    ｭ
    0.13
    POSITIVE LOGITS
    zed
    0.14
     Fault
    0.14
     устра
    0.14
     jeśli
    0.13
    如果没有
    0.13
    ikon
    0.13
    unger
    0.13
    second
    0.13
     Kind
    0.13
    ARK
    0.13
    Activations Density 0.029%

    No Known Activations