© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 199107
    Prev
    Next
    INDEX
    Explanations

    names

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    ILE
    0.38
     சர
    0.37
     *>(
    0.36
    ruch
    0.36
     brach
    0.36
    ضه
    0.36
     delusion
    0.36
    peh
    0.36
    allery
    0.35
     иллю
    0.35
    POSITIVE LOGITS
     Garbage
    0.43
     Baxter
    0.43
     garbage
    0.42
    Gilbert
    0.42
    }_{+}^{
    0.40
     Rights
    0.40
     Gilbert
    0.40
     banker
    0.40
    قیم
    0.40
     असंख्य
    0.39
    Activations Density 0.003%

    No Known Activations