© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 82176
    Prev
    Next
    INDEX
    Explanations

    resource declaration

    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_29_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
     Haram
    0.44
     descoper
    0.39
     dail
    0.38
    stuk
    0.37
    äub
    0.37
    继
    0.36
    arının
    0.36
    ൻ
    0.36
     Bor
    0.36
     Hond
    0.36
    POSITIVE LOGITS
     علاوه
    0.39
    臨時
    0.36
    還是
    0.36
    殘
    0.36
    aside
    0.35
    لای
    0.34
    діть
    0.33
    残
    0.33
    鸷
    0.33
     العنوان
    0.33
    Activations Density 0.002%

    No Known Activations