© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 198986
    Prev
    Next
    INDEX
    Explanations

    template class typename

    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_15_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
    renew
    0.55
    ğı
    0.54
     ဟ
    0.54
     της
    0.52
     Anxiety
    0.52
     بجائے
    0.52
     unlike
    0.51
    ⤒
    0.50
    bors
    0.50
     epistem
    0.50
    POSITIVE LOGITS
    ือก
    0.43
    dg
    0.42
    起
    0.41
     реги
    0.41
    يد
    0.41
    里面的
    0.41
     Nama
    0.40
    сть
    0.39
    ﮔ
    0.39
     propietario
    0.39
    Activations Density 0.000%

    No Known Activations