© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171029
    Prev
    Next
    INDEX
    Explanations

    harmful thoughts or urges

    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_20_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
    .​​
    0.42
     NED
    0.39
     επιχει
    0.39
    opoly
    0.38
    ...”
    0.38
    IN
    0.38
     leave
    0.38
     যাই
    0.38
    住
    0.38
    $(\
    0.38
    POSITIVE LOGITS
     pierced
    0.47
     kecepatan
    0.47
    壹百
    0.46
     सलू
    0.46
     partai
    0.46
    суль
    0.45
    Ⲥ
    0.43
     ribbed
    0.42
    জনাব
    0.41
    ноп
    0.41
    Activations Density 0.008%

    No Known Activations