© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 218520
    Prev
    Next
    INDEX
    Explanations

    change, client, job

    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_47_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
    换
    2.28
    換
    2.13
    更换
    2.00
     swapping
    1.97
    交換
    1.93
     Wechsel
    1.91
     swap
    1.88
     cambio
    1.86
     intercamb
    1.85
    交换
    1.84
    POSITIVE LOGITS
     खाने
    0.36
    Autowired
    0.36
     abortion
    0.36
    andelier
    0.35
     ষড়যন্ত্র
    0.34
    onResume
    0.34
    غذ
    0.34
    楶
    0.33
    PreferenceKeys
    0.33
    wehr
    0.33
    Activations Density 0.098%

    No Known Activations