© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 194226
    Prev
    Next
    INDEX
    Explanations

    .net context

    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_27_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
    -
    0.45
     /
    0.43
    _
    0.43
    、
    0.42
     или
    0.42
     desir
    0.41
     shine
    0.40
     cra
    0.39
     blancas
    0.39
     の
    0.38
    POSITIVE LOGITS
    astos
    0.39
    wnież
    0.39
    rógeno
    0.39
    icky
    0.39
     চালানোর
    0.38
    Chim
    0.38
    ँची
    0.38
    ంచ్
    0.38
     ধ্বংস
    0.37
    Disposable
    0.37
    Activations Density 0.007%

    No Known Activations