© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80268
    Prev
    Next
    INDEX
    Explanations

    guilty trope

    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_0_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
    al
    1.74
    1
    1.56
    -
    1.56
    5
    1.52
    ol
    1.42
    3
    1.27
    am
    1.25
    ili
    1.23
    。“
    1.22
    ।
    1.21
    POSITIVE LOGITS
    િ
    1.27
    джи
    1.19
    بيه
    1.18
     for
    1.15
    其他
    1.15
    "--
    1.11
    it
    1.09
     HBase
    1.08
    "});
    1.07
    ка
    1.05
    Activations Density 0.000%

    No Known Activations