© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 194805
    Prev
    Next
    INDEX
    Explanations

    actions after verbs

    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_27_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
    娜
    0.47
    eraient
    0.43
     ஷ
    0.39
    était
    0.38
    伴
    0.36
     थीं
    0.35
     wollte
    0.34
     ऑ
    0.34
     waren
    0.34
     sarebbe
    0.34
    POSITIVE LOGITS
     becomes
    0.48
    됩니다
    0.48
     됩니다
    0.47
     करिकुलम
    0.45
    کروچ
    0.43
     gets
    0.43
    becomes
    0.42
     fastball
    0.42
    けます
    0.41
     된다
    0.40
    Activations Density 0.023%

    No Known Activations