© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36473
    Prev
    Next
    INDEX
    Explanations

    help people or tasks

    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
    t
    0.63
    urados
    0.58
     memakai
    0.57
     sacrificed
    0.53
     suicides
    0.52
    गुड
    0.52
     hindered
    0.51
    acen
    0.51
    ፃ
    0.51
    datasets
    0.51
    POSITIVE LOGITS
     Y
    0.62
     但是
    0.59
     时间
    0.58
    㖪
    0.55
     umož
    0.54
     Time
    0.54
    իտ
    0.54
     Defense
    0.53
     下载
    0.53
     那麼
    0.53
    Activations Density 0.000%

    No Known Activations