© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 51050
    Prev
    Next
    INDEX
    Explanations

    heard something

    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_31_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
     මෙම
    0.41
    琛
    0.39
    Makeup
    0.38
     Gelegenheit
    0.38
    RECEIVED
    0.38
    strMeal
    0.37
    indungan
    0.37
    Suggestion
    0.37
     analysed
    0.37
    を受けた
    0.37
    POSITIVE LOGITS
     applies
    0.40
    ⏭
    0.38
     تاریخ
    0.38
    cutting
    0.37
    burnt
    0.36
     apply
    0.36
     hems
    0.36
     applying
    0.36
     পুর্ব
    0.36
     Blocking
    0.36
    Activations Density 0.002%

    No Known Activations